Reserved topic scholarships

Intellectual Property Notice for PhD candidates under the UniTrento-FBK Agreement 
Please read the following information carefully before submitting your application. 
Intellectual Property of Research Results.The intellectual property rights of research results generated by PhD students under scholarships within the UniTrento-FBK Agreement shall belong to FBK.
Transfer of Intellectual Property Rights. FBK will establish agreements with PhD students regarding the transfer of intellectual property rights related to their research results.
Collaboration with UniTrento. If UniTrento academic staff contribute to research results obtained through PhD scholarships funded by FBK, the determination of IP shares will be defined through separate written agreements based on each party’s contribution. PhD students are required to collaborate with UniTrento in all necessary activities related to the joint management of IP.

Department of Information Engineering and Computer Science

A1 - Architectures and Representations for Robust Multimodal AI (project:GUIDANCE (Debugging Computer Vision Models via Controlled Cross- modal Generation) FIS2023-03251 – CUP E53C25000420001) (1 grant)

This PhD project will advance multimodal artificial intelligence through three key objectives: designing universal representations that integrate and generalize across modalities like text and vision; analyzing existing architectures to identify limitations such as resolution loss and perceptual degradation; and developing novel structural paradigms to enhance scalability and perceptual precision. Together, these efforts aim to create more robust, efficient, and generalizable multimodal AI systems. This research is supported by the project GUIDANCE (Debugging Computer Vision Models via Controlled Cross-modal Generation) FIS2023-03251 – CUP E53C25000420001

Contact: Niculae Sebe niculae.sebe@unitn.it

A2 - Efficient Foundation Models for Resource-Constrained Visual Understanding (project: UE EDF RA - ARCHYTAS, n. 101167870; CUP: E63C24002180006) (1 grant)

Recent breakthroughs in deep learning have greatly improved visual understanding, but often at the expense of efficiency. Mainstream computer vision models typically do not consider constraints like energy use, memory footprint, and carbon emissions. However, these factors become critical when deploying on resource-limited platforms such as mobile devices, wearables, and drones. This PhD project will explore the design of efficient foundation models, focusing on compact architectures and strategies for balancing accuracy with computational cost.

Contact: Elisa Ricci e.ricci@unitn.it Flavio Vella flavio.vella@unitn.it

A3 - Unified representation learning for multimodal systems (project: GUIDANCE (Debugging Computer Vision Models via Controlled Cross-modal Generation) FIS2023-03251 – CUP E53C25000420001)   (1 grant)

This PhD project will explore unified representation learning for multimodal systems, with a primary focus on vision-language integration. Specifically, the project will investigate architectures for cross-modal understanding, diagnose limitations in existing frameworks (e.g., insufficient unification, loss of granular perceptual detail), and develop novel solutions to address these challenges. This research is supported by the project GUIDANCE (Debugging Computer Vision Models via Controlled Cross-modal Generation) FIS2023-03251 – CUP E53C25000420001.

Contact: Niculae Sebe niculae.sebe@unitn.it

​​​​​​B1 - Algorithm and Runtime Co-Design for Efficient AI on Heterogeneous Architectures (project UE EDF RA - ARCHYTAS, n. 101167870; CUP: E63C24002180006) (1 grant)

This research investigates methods to optimise the training and inference of modern AI models in distributed, heterogeneous computing environments, with emphasis on scalable performance, efficient communication, and energy-aware execution. The growing complexity of AI models, characterised by deep architectures, large parameter counts, and irregular data patterns, poses significant challenges for multi-node, multi-accelerator systems.
The candidate will explore parallelism strategies (data, pipeline, tensor/model parallelism) and analyse how system-level factors, such as batch size, input structure, compute-to-communication ratio, and network topology, affect performance. The goal is to identify bottlenecks and develop parallel algorithms and adaptive strategies for efficient and portable execution by following a hardware/network model co-design approach.
Transformer-based and graph-structured models will serve as representative workloads to evaluate diverse computation and communication patterns. The research may also target the orchestration of heterogeneous components, such as general-purpose accelerators, SmartNICs, and processing-in-memory (PIM) units, through runtime systems supporting asynchronous communication, collective offloading, and energy-performance trade-offs.
Required and desired skills:
•        Solid background in parallel and distributed architectures
•        Solid background in modern Machine Learning models 
•        Experience with modern AI frameworks (e.g., PyTorch, TensorFlow)
•        Familiarity with shared-memory programming with GPUs (e.g., SYCL , HiP, CUDA or similar)
•        Knowledge of distributed-memory model and communication libraries (e.g., MPI, *CCL)
•        Experience with performance profiling and benchmarking tools

Contact: Flavio Vella flavio.vella@unitn.it

​​​​​​B2 - Design and Integration of a Hardware Description Language for Optoelectronic Accelerators in Artificial Intelligence (Project UE EDF RA - ARCHYTAS, n. 101167870; CUP: E63C24002180006) (1 grant)

This research aims at the development of comprehensive software frameworks for controlling and programming photonic integrated circuits (PICs), drawing explicit parallels to how VHDL enables electronic function implementation on FPGA hardware. As photonic computing emerges as a promising solution to overcome electronic computing limitations, there remains
a significant gap in the standardization and accessibility of software interfaces for photonic hardware. The proposed research aims to develop a unified hardware description language specifically tailored for photonic systems, enabling designers to abstract complex optical phenomena into programmable components. By creating a "Photonic-HDL" equivalent to VHDL, this work will address current challenges in photonic circuit design, simulation, verification, and implementation. The research methodology will involve analyzing existing photonic design paradigms, developing suitable abstraction models, creating compiler frameworks for photonic netlists, and demonstrating practical implementations on current photonic hardware platforms.

Contact: Philippe Velha philippe.velha@unitn.it Flavio Vella flavio.vella@unitn.it

​​​​​​B3 - Low-power and batteryless wireless networking and localization (1 grant)

Low-power wireless devices are at the cornerstone of the Internet of Things (IoT), for which they provide two fundamental functionalities: the ability to interconnect devices (networking) and to determine their position in space (localization). 
The core research challenges lie in achieving high reliability and low latency with only a small energy budget. In this respect, batteryless systems push the need for low-power operation even further. These systems typically rely on supercapacitors that remove the dependance on batteries, greatly simplifying mainteinance and reducing environmental impact. However, their available energy is significantly smaller w.r.t. batteries and depleted more rapidly than it is repleted via external sources, e.g., energy harvesters. This mode of operation, alternating activity and recharging periods, results in "intermittent computing", expected to pave the way to a batteryless IoT but also significantly amplifying the challenges above. 

The PhD student will explore research themes at the intersection of networking and localization along with the challenges and limits of batteryless, intermittent computing, with the goal of contributing new techniques enabling new tradeoffs between application requirements and expected performance. The reference radio technologies for these research efforts will be ultra-wideband (UWB) and possibly Bluetooth, although others (e.g., IEEE 802.15.4, LoRa, backscatter) are also within scope.

The activities carried out can be characterized as "systems research". Novel ideas and contributions are embodied in prototypes concretely demonstrating feasibility and improvements over the state of the art. Models are used to characterize the performance of prototypes, which are then evaluated experimentally in realistic setups. In this respect, the research group offers unique assets, including a 130-node (~8000sqm) indoor UWB testbed and two accurate (mm-level) optical facilities, and along with real-world use cases from ongoing projects. 

Contact: Gian Pietro Picco gianpietro.picco@unitn.it

B4 - Scalable Parallel Algorithms for Efficient Attention-Based Learning on Emerging Computing Systems (project: UE EDF RA - ARCHYTAS, n. 101167870; CUP: E63C24002180006) (1 grant)

The proposed research aims to develop advanced parallel algorithms and system-level optimizations for the efficient execution of attention-based machine learning models, such as Transformers. The goal is to ensure scalability across a wide range of computing platforms, from resource-constrained embedded devices to high-performance computing (HPC) systems used in scientific and industrial applications. The project will focus on practical and broadly applicable solutions, with particular emphasis on dynamic quantization and sparsification techniques that reduce computational complexity, memory usage, and energy consumption, while preserving model accuracy. Fine-grained parallelization strategies and architectural optimizations will also be explored, leveraging modern software tools and libraries to enable efficient deployment on heterogeneous platforms. Ultimately, the research seeks to make Transformer-based models viable even in scenarios where efficiency is a critical constraint, promoting the use of artificial intelligence across a diverse set of domains, from edge computing to large-scale scientific discovery.
Ideal Candidate skills are:
•        Strong expertise in parallel computing, computer architecture, and system-level optimizations. 
•        Experience with quantization, sparsification, or hardware-software co-design techniques for Machine Learning 
•        Advanced proficiency in programming languages including C++, CUDA, and similar high-performance languages.
•        Hands-on experience in working with Parallel Architectures and Accelerators like GPUs. AI accelerators or embedded systems are a plus. 
•        Excellent analytical, problem-solving, and system-design capabilities.

Contact: Giovanni Iacca giovanni.iacca@unitn.it Flavio Vella flavio.vella@unitn.it

B7 - Advanced techniques for AI application to robotic manipulation (project: UE HE MAGICIAN, G.A. 101120731, CUP: E63C2300073000) (1 grant)

The PhD student will develop AI techniques for the control and motion planning of robotic manipulators. The project will particularly focus on scenarios in which the presence of humans makes the environment highly unpredictable, while also increasing the demands on safety and user acceptability. Potential application areas include manufacturing and medical robotics

Contact: Luigi Palopoli luigi.palopoli@unitn.it Daniele Fontanelli daniele.fontanelli@unitn.it

Additional scholarships (published on 05.08.2025)      B9 - Security of satellite communications (1 grant) 

Satellite communication systems (SatComs) enable a vast range of services. These systems underpin technologies such as GPS and navigation, weather prediction, military communications, broadcast radio, and tracking and communications for aviation and maritime industries. The complexity of their design, the hostile conditions of space, and, in some cases, insufficient consideration of security during development expose these systems to numerous potential threats.
While considerable research has been devoted to securing satellite communication infrastructures, they continue to face diverse cyber-physical risks. Common attack vectors include signal interception, manipulation, deliberate interference (jamming), traffic redirection, service disruption, and spoofing. As the demand for next-generation connectivity grows—these vulnerabilities become even more critical.
Future networks will depend heavily on advanced SatComs to bridge connectivity gaps, deliver ultra-low latency, and integrate seamlessly with terrestrial infrastructure. Of particular interest are the security aspects of the interactions between SatComs and aerial communications.
This PhD project focuses on addressing the pressing challenges of security and resilience within current and emerging SatComs ecosystems. The aim is to uncover how cross-domain interactions between cyber and physical elements can be harnessed to enhance the reliability, security, and adaptability of SatComs and future global communication frameworks.

Contact: Bruno Crispo bruno.crispo@unitn.it

C1 - Agentic AI for Adaptive Autonomy: Architectures and Mechanisms for Self-Improving Autonomous Agent (1 grant)

This project explores how future AI agents can go beyond static a predesigned behavior and continuously adapt, learn, and evolve—not just react, but reflect and improve over time. If you’re passionate about autonomous systems, agent architectures, or self-improving and evolving  AI, this is a unique opportunity to contribute to cutting-edge research at the intersection of AI, autonomy, and software engineering.
Topics may include:

• Agentic architectures and self-reflective loops
• Intention revision and plan adaptation
• Learning from interaction and experience
• Long-term autonomy and dynamic goal management

Contact: Paolo Giorgini paolo.giorgini@unitn.it

C2 - Innovative education for social impacts of computer science (1 grant)

This doctoral grant aims to work on the design, development, and validation of innovative pedagogical methods for the teaching of social impacts of computing for computer science students, with a special attention towards education methods based on live-action roleplay (larp/EduLARP). The candidate's work will engage the intersection of the Computer Science Education, Computing and Society, and larp game design research communities, work working towards filling the research and educational gap on the creation of context-rich educational practices that are able to engage students and stimulate them in the development of Social, Ethics, and Professional (SEP) competences. Many activities will synergise with the many European collaborations that are active in the research group, with the ambition to explore new collaboration opportunities. Ideal candidates will have (or will aim to develop) a highly interdisciplinary profile that combines a background and/or interest in computer science, sociology of technology, innovative pedagogy, and game design. 

Contact: Lorenzo Angeli lorenzo.angeli@unitn.it Maurizio Marchese maurizio.marchese@unitn.it

D4 - Satellite ground penetrating radar for mapping and monitoring ice in the Earth's polar regions (1 grant)

A major source of uncertainty for climate models is related to the limited understanding of the conditions of the polar ice sheets in Greenland and Antarctica. This is due to the lack of satellite missions capable to measure the status of the ice from the surface to the bedrock. Recent studies and research activities resulted in the definition of the SaTellite RAdar sounder for earTh sUbsurface Sensing (STRATUS) mission concept. STRATUS is a satellite mission for Earth Observation with an innovative VHR distributed radar sounder (RS) having the unique capability to obtain continuous and large-scale subsurface measurements in the polar ice to get new fundamental data that have not been acquired by any other past or present
remote sensing mission on the Earth. The distributed radar sounder is based on a flying formation that implements a multistatic radar.
The research activities of this grant are related to the STRATUS concept. The research will be focused on at least two of the following topics:
1) design, implementation and validation of novel methodologies for the modeling of the ice sheets and ice shelves and the related simulation of the radar sounder data.
2) Design, implementation and validation of the signal processing techniques needed for the processing of the data acquired by the flying formation and the generation of the raw data products.
3) Design, implementation and validation of data analysis techniques based on artificial intelligence for the generation of high level radar sounder products.
These activities will consider new concepts and methods and are expected to result in very relevant scientific returns. Research will be developed at the University of Trento, Department of Information Engineering and Computer Science, Remote Sensing Laboratory (https://rslab.disi.unitn.it/).

Contact: Lorenzo Bruzzone lorenzo.bruzzone@unitn.it

D5 - Machine learning methodologies for the analysis of images and data acquired by planetary radars (Project: ASI Missione JUICE Bruzzone, GA 2023-6-HH.0, CUP: F83C23000070005)  (1 grant)

Space missions for the exploration of planets and celestial bodies in the Solar system are very important for the huge scientific and technological return associated with them. Some of the most challenging science objectives of these missions are related to the analysis of sub-surface processes that are of crucial importance for many different implications they have. The research activities of this grant are related to planetary radar sounders, which are instruments for the study of the subsurface of the planets of the Solar system. These radars operate from satellite platforms and acquire images related to the subsurface of celestial bodies that can results in groundbreaking science results. The activity will be focused on the development of methodologies for the processing and the automatic analysis of these data. Special emphasis will be given to methodologies that exploit the most recent developments in the framework of machine learning and signal processing.
Research will be developed at the Remote Sensing Laboratory (https://rslab.disi.unitn.it/) and will be related to the Radar for Icy Moon Exploration (RIME) on board of the JUpiter ICy moons Explorer (JUICE) of the European Space Agency (see https://www.esa.int/Science_Exploration/Space_Science/Juice  for more details on the mission).

Contact: Lorenzo Bruzzone lorenzo.bruzzone@unitn.it

Fondazione Bruno Kessler (FBK)

A4 - Combining GeoAI and multi-modal LLM to retrieve spatial-temporal information from historical data (1 grant)

GeoAI and LLM are transforming the way we can understand and manage spatial and temporal large-scale data and territorial phenomena. The PhD project will be focused on the exploitation of historical geospatial data - from historical maps to terrestrial, aerial and satellite imagery -  alongside textual sources within a multi-modality framework. By integrating AI solutions, including LLMs, VLMs and MMLLM, the project aims to extract, structure and analyze complex geospatial information and changes over urban, forestry or glacial areas. The PhD outcomes will enhance the accessibility and understanding of historical geospatial data, boost their usage and allow for comprehensive cross-disciplinary analyses and insights into historical events and territorial transformations.

Contact: Fabio Remondino remondino@fbk.eu

A5 - Dynamic Personas: Modeling the Evolution of Opinions and Values in LLMs (1 grant)

Previous research has focused on equipping conversational agents with static, deep personas incorporating opinions, values, and beliefs to enrich dialogues. However, human interaction is dynamic; opinions can shift, and values may be expressed differently depending on context or interlocutor. Current persona-based models lack the ability to adapt or evolve during interaction.
This PhD Thesis aims to address this gap by developing neural models capable of representing and evolving deep personas dynamically within a conversation. The research will investigate how to model the triggers and mechanisms of persona adaptation, such as responding to conversational context, user interaction history, or explicit feedback. The goal is to create agents whose expressed opinions and values can evolve coherently over time, leading to more natural, engaging, and long-term interactions. Evaluation will focus on the plausibility, coherence, and adaptability of the dynamic persona, with a focus on understanding how LLMs' personas impact user perception and interaction quality.

Contact: Marco Guerini m.guerini@fbk.eu

A6 - Knowledge-Driven Natural Language Generation for Combating Online Harms (1 grant)

The pervasive spread of online misinformation and hate speech poses critical threats to societal well-being and democratic discourse. While neural language models (NLMs) show promise in generating counter-arguments and debunking fake news, they often suffer from limitations such as hallucination, knowledge scarcity, and a lack of sophisticated argumentative reasoning. This PhD project aims to overcome these shortcomings by developing novel knowledge-driven neural language generation pipelines. We will focus on integrating diverse external knowledge sources, principles from argumentation theory, and domain-specific features to enable the generation of factually accurate, persuasive, and ethically sound counterspeech. The goal is to build advanced generative AI systems that can effectively and safely mitigate the impact of both misinformation and hate speech online.

Contact: Marco Guerini m.guerini@fbk.eu

B5 - Dependable AI-Driven Anomaly Detection for Securing Industrial Control Systems (1 grant)

Industrial Control Systems (ICS) are foundational to critical infrastructure sectors such as energy, water, transportation, and manufacturing. However, the increasing connectivity of ICS to corporate networks and the Internet has exposed them to a growing number of cyber and operational threats. Traditional security and monitoring mechanisms often fall short due to the complexity, real-time constraints, and high availability requirements of these systems.
This PhD project aims to develop dependable, AI-driven anomaly detection techniques tailored for ICS environments. The research will explore the integration of robust machine learning algorithms, including deep learning and hybrid models, capable of identifying both known and unknown anomalies across multi-modal data sources (e.g., network traffic, sensor readings, control commands). A key focus will be on ensuring dependability, including robustness to open-world challenges such as concept-drift and adversarial machine learning attacks.
The candidate will investigate approaches for real-time detection, adaptive learning in dynamic environments, and explainable AI (XAI) to support human-in-the-loop decision-making. The project will involve collaborations with industry partners and use realistic ICS testbeds or simulation platforms to validate performance and generalizability.

Contact: Roberto Doriguzzi Corin rdoriguzzi@fbk.eu

B6 - Secure AI-Focused Programming and Regulatory Software Compliance (1 grant)

The global workforce is facing critical staff shortages due to aging populations and declining birth rates. This demographic shift threatens productivity, especially in fields like computer science and cybersecurity, where demand for skilled professionals is rising alongside system complexity and regulatory requirements (Piras et al. 2020). As ICT companies expand, the need for software and security engineers grows, yet programming remains a time-consuming and intricate task.
To sustain productivity, automation and optimisation are essential. These strategies streamline the software engineering cycle by enabling higher abstraction levels, reducing time and resource demands, and improving code security. AI offers promising support, such as tools that generate code (Vaithilingam et al. 2022). However, current AI-generated code often contains errors and lacks scalability, requiring manual debugging and refinement. While AI can produce valid snippets, it struggles to create complete, secure systems at scale.
A promising solution is decomposing complex systems into smaller sub-problems, allowing AI to generate components more effectively. Goal Modeling (GM) techniques are well-established for this purpose, enabling hierarchical decomposition of requirements (Horkoff et al. 2019). GM and visual programming help developers work at higher abstraction levels, potentially accelerating design.
We hypothesize that combining GM with AI can democratize software development, enabling broader participation beyond traditional programmers. Integrating this approach with Symbolic AI, Neuro-Symbolic AI, Agentic AI, Neural Networks for code vulnerability detection (Senanayake et al. 2024), SBOM tools, prompt vulnerability detectors, and static/dynamic analysis tools could enhance code security and regulatory compliance (Piras et al. 2020). These synergies could empower diverse professionals to contribute to software engineering, helping address workforce shortages while building secure, high-quality systems.
This research proposes designing a secure, AI-enhanced goal-modeling framework to support rapid software development with reduced skill requirements. By “secure,” we refer to integrating software security measures and ensuring compliance with regulations like the EU AI Act, NIS2 and GDPR (Piras et al. 2020). The research may focus on conceptualizing and prototyping this framework, identifying key components, and evaluating it in realistic or industrial settings, potentially in collaboration with industry partners.

REFERENCES
Horkoff, J. et al. Goal-oriented requirements engineering: an extended systematic mapping study. Journal of Requirements Engineering, 2017.
Piras, L. et al. “DEFeND DSM: A Data Scope Management Service for Model-Based Privacy by Design GDPR Compliance” in Int. Conf. on Trust, Privacy and Security in Digital Business (TrustBus). Springer, 2020.
Senanayake, J. et al. Defendroid: Real-time Android code vulnerability detection via blockchain federated neural network with XAI. Journal of Information Security and Applications, 2024.
Vaithilingam, P. et al. Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. CHI Conference, 2022

Contact: Luca Piras l.piras@fbk.eu

C3 - Certifying model checking (1 grant)

In the field of formal verification, certifying proofs serve as compelling evidence to demonstrate the correctness of a model within a deductive system. These proofs can be automatically generated as a by-product of the verification process and are key artifacts for high-assurance systems. Their significance lies in their ability to be independently verified by proof checkers, which provides a more convenient approach than certifying the tools that generate them.
Model checking is one of the leading formal techniques used in the domain of hardware verification and synthesis, and it relies on an algorithmic exploration of the system's state space to ensure that the system behaves as expected over time. 
Modern model checking tools are sophisticated pieces of software, employing a wide range of diverse techniques to increase their performance, effectiveness, and scalability to real-world problem instances. Although often their underlying algorithms are capable of producing some form of proof, ensuring that such core proofs are compatible with the transformation and optimization
techniques applied to the input system remains a challenge.
The objective of this project is that of developing novel techniques for the reconstruction of proofs in model checking, so as to be able to certify their results. We will consider different proof formalisms and certification strategies, leveraging both interactive theorem provers and automatic decision
procedures based on propositional satisfiability (SAT) and satisfiability modulo theories (SMT). The candidate is expected to explore not only explore theoretical results, but also practical implementations on state-of-the-art model checking tools developed at FBK, and their applications to real-world problems.

Contact: Alberto Griggio griggio@fbk.eu

C4 - Failure analysis and safety assessment of complex industrial systems (1 grant)

Industrial systems are reaching an unprecedented degree of complexity. The design process has to guarantee not only the functional correctness of the implemented system, but also its dependability and resilience with respect to run-time faults. Hence, the design process must characterize the likelihood of faults, mitigate possible failures, and assess the effectiveness of the adopted mitigation measures.  
Formal methods have been increasingly used over the last decades to deal with the shortcomings of designing complex systems, in different domains. Formal methods are based on the adoption of a formal, mathematical model of the system, shared between all actors involved in the system design, and on a tool-supported methodology to aid all the steps of the design, from the definition of the architecture down to the final implementation in HW and SW. Formal methods include technologies such as model checking, an automatic technique to symbolically and exhaustively analyze all possible executions of the system in the formal model, in order to detect design flaws as early as possible. Model checking techniques have been recently extended to assess the safety and dependability characteristics of the design, and for system certification. 
The objective of this study is to advance the state-of-the-art in failure analysis and safety assessment of complex industrial systems. In particular, it will investigate extensions of existing fault propagation models and failure analysis techniques to deal with aspects such as the timing of fault propagation, the impact on system degradation, the characterization of transient and sporadic faults, and the analysis of the effectiveness of fault mitigation measures in presence of complex fault patterns. Moreover, this study will address the formal design of fault detection, isolation, and recovery (FDIR) sub-systems, techniques for diagnosis and root-cause analysis using formal methods,  anomaly detection and FDIR based on machine learning techniques. 
The developed techniques will be implemented and evaluated using tools for system-software engineering such as the COMPASS and the TASTE tools. This study is aligned with the topics investigated in various industrial projects carried out at FBK, such as the COMPASTA and AIFDIR projects, funded by the European and Italian Space Agencies.

Contact: Marco Bozzano bozzano@fbk.eu 

C5 - SMT-based software model checking (1 grant)

Techniques based on formal methods for the verification and validation of software systems are becoming increasingly important, due to the growing complexity and importance of such systems in every aspect of modern society. Despite the major progress and various examples of success stories, however, the application of formal methods, and especially automatic or fully-automatic techniques, in software remains a challenge in practice.
This project will investigate novel techniques for the application of formal methods to the design, verification, and validation of software, with particular emphasis on safety-critical application domains such as railways, automotive, avionics, and aerospace. The primary focus will be on automatic techniques combining model checking and automated theorem proving based on the Satisfiability Modulo Theories (SMT) paradigm, but other related techniques such as interactive theorem proving, abstract interpretation, or deductive verification will be considered as well. Examples of the problems tackled during the project include the formal verification of functional requirements  expressed in temporal logics, automated test-case generation, efficient handling of parametric/multi-configuration software systems and product lines, and the verification of software operating in a physical environment, subject to real-time constraints. Importantly, in addition to researching novel theoretical results, a significant part of the project activities will be devoted to the implementation of the techniques in state-of-the-art verification tools developed at FBK and their application to real-world problems in collaboration with our industrial partners.

Contact: Alberto Griggio griggio@fbk.eu

C6 - Testing methodologies for complex configurable systems (1 grant)

The escalating complexity of software systems requires the development of novel methodologies and tools for designing and testing software systems exhibiting high variability with respect to potential functional configurations in combination with different release architectures. The primary objective of this research is to investigate innovative approaches to the testing, verification, and validation of such systems, which entail the collaborative utilisation of model-based and AI-driven techniques, including formal methods, machine learning, and optimisation.

Contact: Angelo Susi susi@fbk.eu

D1 - Artificial intelligence for Earth monitoring (1 grant)

The recent Earth Observation missions like (ESA Copernicus - Sentinels, ASI PRISMA and COSMO-SkyMed, and future IRIDE constellation) make available databases of long, dense and worldwide image time series. The data have complex spatio-spectro-temporal behaviors and variability, and they show irregularities and misalignments.
Candidates will be requested to develop novel methodologies within the artificial intelligence framework for effectively and efficiently process image time series for semantic segmentation, target detection and change detection across multiannual series of data. Methodologies like foundational models, machine learning, deep learning, multitask learning, enforcement learning, etc. will be considered.
Besides the requirements established by the rules of the ICT school, preferential characteristics for candidates for this scholarship are:
•    master degree in Electrical Engineering, Communication Engineering, Computer/Data Science, Mathematics or equivalents;
•    background in artificial intelligence, image/signal processing, remote sensing, passive/active sensors.

Contact: Francesca Bovolo bovolo@fbk.eu

D2 - Bridging Space and Soil: AI-Driven Insights from Satellite and IoT Data for Smart Farming (1 grant)

The rapid advancement of Earth observation satellite constellations and the widespread deployment of IoT-based environmental sensors present an unprecedented opportunity to transform data-driven environmental modeling in precision agriculture. This PhD scholarship will explore the integration of multi-source remote sensing data with classical Machine Learning and integrative AI techniques to enhance the understanding and prediction of vegetation dynamics, soil moisture variability, and water use efficiency. By combining high-resolution satellite imagery, hyperspectral data, real-time IoT sensor networks, and data from autonomous vehicles, this study aims to develop next-generation vegetation indices and process-based models for improved agricultural monitoring and ecosystem management. The research will focus on advancing data fusion methodologies, developing scalable AI-driven models, and validating them against ground-truth datasets to enhance decision-making in precision agriculture and promote environmental sustainability.

Contact: Fabio Antonelli fantonelli@fbk.eu

D3 - Radar sounder data processing and information extraction for space exploration (project: ASI-INAF n. 2023-6-HH.0 JUICE-RIME-E - CUP: F83C23000070005) (1 grant)

In the context of the European Space Agency (ESA) mission JUpiter ICy moons Explorer (JUICE) to the Jovian system, we seek for candidates willing do develop methodologies for radar sounder data processing (data enhancement, semantic segmentation, denoising, content based retrieval, target detection, multitemporal analysis, radar mapping, etc.). The outcome of this activity will contribute in improving the understanding of the subsurface of planetary bodies, the correlation to history and climate as well as to a better understanding of the Earth.
The candidate will be requested to design and develop novel methodologies within artificial intelligence framework (machine learning, deep learning, quantum-based learning, etc.) for effective information extraction from radar sounder data.
Besides the requirements established by the rules of the ICT school, preferential characteristics for candidates for this scholarship are:
•    master degree in Electrical Engineering, Communication Engineering, Computer/Data Science, Mathematics or equivalents;
•    knowledge in artificial intelligence, image/signal processing, remote sensing, radar remote sensing.

Contact: Francesca Bovolo bovolo@fbk.eu

National Cybersecurity Agency (NCA) 

Additional scholarship (published on 05.08.2025)

B8 - AI-Aided Extraction of Key Risk Indicators and Security KPIs (CUP E66E25000010001) (1 grant)

This fellowship is funded by the Italian Cyber Security Agency (ACN - Agenzia per la Cybersicurezza Nazionale - link). The  PhD Student must comply with the additional regulations (https://www.acn.gov.it/portale/documents/20119/792856/ACN_Dottorati_XLI_ciclo_DISCIPLINARE_All.1.pdf/d9742e43-7e54-8d01-aa3a-eb1f6e0183ad?t=1740409658551)

The high-level objective is to define a semi-automated AI-based pipeline to extract business processes at a high level from existing documents and automatically associate them with both risk calculations (Key Risk Indicators) and the corresponding security objectives (Key Security Indicators).
The project includes five sub-objectives:

• O1: The state of the art in activities related to extracting elements of Risk Assessment and Threat Intelligence from documents using Large Language Models (LLMs), which is already a well-researched area and does not require further innovation. LLMs alone are not capable of performing even minimally satisfactory risk assessments (https://doi.org/10.1111/risa.14351)
• O2: Risk procedures on which to define transient mathematical structures (e.g., hypergraphs) that can capture organizational structure and correspondingly associate risks and mitigation strategies. This activity was previously conducted by the PI both for privacy (https://doi.org/10.1016/j.csi.2005.01.003) and for security (https://doi.org/10.1109/RE.2005.43), but the main problem with these and similar methodologies is the manual effort required for extraction, where an expert must elicit such policies.
• O3: Construction of a comprehensive pipeline that will use the mathematical structures to determine Key Risk Indicators of the company and organizational structure. These indicators (at the root of the hypergraph of organizational processes) will then be associated with the Key Security Indicators of the treatment measures (at the leaves of the organizational hypergraph).
• O4: Overall determination of the confidence level of the calculated risk. Indeed, all automated procedures involve errors and approximations, so it will be important for stakeholders to have a confidence interval.
• O5: Case studies, including industrial ones with potential partners, one of which has already been identified during the proposal phase (see below). 

The primary objective of this sub-point of the Agenda is to facilitate the identification of risk elements and consequently their quantification (captured by the Key Risk Indicators), in such a way as to then make the corresponding treatment plan (captured by the Key Security Indicators) more effective. From a purely theoretical point of view, one could start with a definition of acceptable risks and develop the organization and its processes around them. Unfortunately (or fortunately), the organization/company already exists and has processes that often cannot be modified for functional or legal reasons. It is therefore the risk assessment that must take on the burden of capturing what already exists. This capture is typically done “by hand” (for example, by following human-intensive processes typical of ISO 27001 standards) and using automated systems (vulnerability scanners, etc.) on networks or scanners to determine the posture. The result is a total dichotomy: on one hand, “the paper” that describes the “living” processes and the assets that really matter, and on the other hand, the IT “dashboards” that plot intrusion attempts by the second in a multicolored whirlwind often irrelevant from the point of view of risk and security.

The process will develop through a spiral approach.

• M1–M12 – achievement of objectives O1 and O2 regarding state-of-the-art technologies (subject of a Systematic Literature Review) and identification of requirements for objective O5 (industry paper to be submitted to ICSE-SIEP or ESEM).
• M6–18 – development of new approaches and generation of the O3 pipeline, which will be validated on synthetic datasets or partial examples obtained in the first phase.
• M12–M24 – determination of error propagation methods and development of algorithms to calculate the confidence of risk estimates (O4) (submission to Risk Analysis Journal).
• M18–M36 – refinement of the pipeline (O3) using case studies obtained through industrial collaboration (O5) (submission to IEEE Symposium S&P)
• M36–M42 – submission and defense of the doctoral thesis.

In terms of qualifications, the PI has conducted numerous studies on the automatic and semi-automatic management of risk based on existing data, in collaboration with nationally relevant companies (Poste Italiane https://doi.org/10.1145/2652524.2652585, https://doi.org/10.1111/risa.12864) or international ones (Eurocontrol https://doi.org/10.1007/s10664-023-10321-y, National Grid https://doi.org/10.1109/MSP.2016.48), and major security companies (Symantec https://doi.org/10.1111/risa.13732, Trend Micro https://doi.org/10.1109/TIFS.2024.3456960). He was also the first researcher in the world to propose the use of the Case-Control Study for risk analysis (https://doi.org/10.1145/2630069) — a method successfully used in medicine, for example, to correlate lung cancer risk with smoking — for which he has just developed a further study on corporate risk related to non-compliant behavior (e.g., using company computers to view pornographic websites), determining that not everything is necessarily risky https://doi.org/10.1109/TIFS.2024.3456960). In addition, he is a member of the SIG CVSS (Common Vulnerability Scoring System), named co-author of version 4.0 of the current standard, and FIRST Liaison, thus having direct worldwide access to the expertise used by national entities such as the CSIRT.

The PhD student will be spending a period of six months abroad as part of their studies. 

Contact: Fabio Massacci fabio.massacci@unitn.it Domenico Siracusa domenico.siracusa@unitn.it