Keynote Speakers
Corina Pasareanu
Title: Analysis of Perception Neural Networks via Vision-Language Models
Abstract: The analysis of Deep Neural Networks (DNNs), particularly those used as perception modules, is very challenging due to the networks' complex and opaque decision-making processes. Multi-modal Vision-Language Models (VLMs) such as CLIP offer an exciting opportunity to interpret the representation space of vision models using natural language. VLMs have been trained on a large body of images accompanied by their textual description, and are thus implicitly aware of high-level, human-understandable concepts describing the images. In this talk, we report on on-going work that seeks to leverage VLMs for the formal analysis and run-time monitoring of requirements expressed in terms of natural-language concepts, as well as debugging of perception modules.
Bio: Corina Pasareanu is an ACM Fellow and an IEEE ASE Fellow, working at NASA Ames. She is affiliated with KBR and Carnegie Mellon University's CyLab. Her research interests include model checking, symbolic execution, compositional verification, trustworthy AI, autonomy, and security. She is the recipient of several awards, including ETAPS Test of Time Award (2021), ASE Most Influential Paper Award (2018), ESEC/FSE Test of Time Award (2018), ISSTA Retrospective Impact Paper Award (2018), ACM Impact Paper Award (2010), and ICSE 2010 Most Influential Paper Award (2010). She has been serving as Program/General Chair for several conferences including: FASE 2026, ICSE 2025, SEFM 2021, FM 2021, ICST 2020, ISSTA 2020, ESEC/FSE 2018, CAV 2015, ISSTA 2014, ASE 2011, and NFM 2009. She is on the steering committees for the ICSE, ETAPS, TACAS and ISSTA conferences. She is currently an associate editor for IEEE TSE and for STTT, Springer Nature.
Marsha Chechik
Title: Assuring Product Lines of Software Systems
Abstract: TBD
Bio: Marsha Chechik is Professor and former Chair in the Department of Computer Science at the University of Toronto, where she holds Bell University Labs Chair in Software Engineering. In 2022, she served as Acting Dean in Faculty of Information. Her research interests are in the application of formal methods to improve the quality of software. She has co-authored numerous papers in formal methods, software specification and verification, computer safety and security, and requirements engineering. She is a member of IFIP Working Group 2.9 on Requirements Engineering, an Associate Editor-in-Chief of IEEE Transactions on Software Engineering and Associate Editor-in-Chief of Journal on Software and Systems Modeling. She has been Program Committee Chair of top software engineering and verification conferences: ASE'14, ESEC/FSE'21, TACAS'16, ICSE'18, FM'23, MODELS'24. She is Fellow of ACM, Fellow of Automated Software Engineering and Chair of ACM SIGSOFT.
Michele Nogueira
Title: Data-Driven Resilience: A Double-Edged Sword for Security and Privacy
Abstract: In an increasingly connected and data-rich world, resilience is no longer just about withstanding failures — it's about adapting, learning, and recovering in real time. At the heart of this evolution lies data: vast, dynamic, and increasingly central to decision-making in secure and dependable systems. But while data-driven strategies have opened new frontiers in threat detection, system adaptation, and anomaly prediction, they have also introduced new vulnerabilities. From training set poisoning in machine learning models to metadata leaks in system logs, data can empower both defenders and adversaries. This keynote explores the paradox of data-driven resilience — how the datasets that enable adaptive defense and fault tolerance can also expose systems to novel attack vectors and privacy breaches. Drawing from real-world case studies, research insights, and lessons from critical infrastructures, we will examine the trade-offs inherent in building resilient systems through data.
Bio: Michele Nogueira is an Associate Professor in the Computer Science Department at Federal University of Minas Gerais (UFMG), Brazil. She received her doctorate in Computer Science from the University Pierre et Marie Curie - Sorbonne Université, France. She was on a sabbatical leave at Carnegie Mellon University, USA (2016-2017). Her research interests include wireless networks, network security and dependability. She has worked on providing resilience to self-organized, cognitive and wireless networks by adaptive and opportunistic approaches. Today, her research focuses on creating network security intelligence supported by data science. Dr. Nogueira was one of the pioneers in addressing survivability issues in self-organized wireless networks, being the work “A Survey of Survivability in Mobile Ad Hoc Networks”, one of her prominent scientific contributions. She has been a recipient of Academic Scholarships from Brazilian Government in her undergraduate and graduate years, and of international grants such as from the ACM SIGCOMM Geodiversity program. She served as Associate Technical Editor for the IEEE Communications Magazine. She served as chair for the IEEE ComSoc Internet Technical Committee. She is an ACM and IEEE Senior Member.