Battista Biggio
Venue: TII Yas Auditorium
31st October, 2024, 2:00PM - 3:00PM (GST)
| Title: | AI Security Testing: lessons learned and future challenges |
| Abstract: | Security testing of machine-learning (ML) models has become crucial due to the widespread use of AI-based solutions in safety-critical and security-sensitive systems and to comply with emerging regulations. While there is a general agreement on the need to secure ML models, defining a constructive notion of security for an ML-based system remains unclear and strongly application-dependent. This talk aims to shed light on the main factors that are hindering progress in this field. These include the lack of an underlying, systematic, and scalable (risk-based) framework to properly evaluate machine-learning models under adversarial and out-of-distribution scenarios, along with suitable tools for easing their debugging. To this end, I will share the perspective of MLTrustOps that we proposed within the Horizon Europe-funded ELSA project and report concrete examples of what our laboratory has been working on recently to enable a first step towards overcoming these limitations, also in the context of security-related tasks, including malware detection and web security. |
| Bio: | Battista Biggio (MSc 2006, PhD 2010) is a Full Professor at the University of Cagliari, Italy, and co-founder of the cybersecurity company Pluribus One. He has provided pioneering contributions in machine-learning security, playing a leading role in this field. His seminal paper on “Poisoning Attacks against Support Vector Machines” won the prestigious 2022 ICML Test of Time Award. His work on “Wild Patterns” won the 2021 Best Paper Award and Pattern Recognition Medal from Elsevier Pattern Recognition. He has managed more than 10 research projects, and regularly serves as a PC member for ICML and USENIX Security, and as Area Chair for NeurIPS. He chaired IAPR TC1 (2016-2020), co-organized S+SSPR, AISec and DLS, and served as Associate Editor for IEEE TNNLS, IEEE CIM, and Elsevier Pattern Recognition Journal (PRJ). He is now Associate Editor-in-Chief for PRJ. He is also a senior member of IEEE and ACM, and a member of IAPR and ELLIS. |