Security and AI by DGA
PITCH
The European Symposium on Security and AI (ESSAI) will hold its first edition during European Cyber Week (ECW) on November 20 and 21, 2024.
This event, co-organized by AMIAD (Agence Ministérielle de l'Intelligence Artificielle de Défense) and INRIA (French national institute of research in digital science and technology), feature a program of three themed sessions focusing on:
-
The security of artificial intelligence systems, covering topics such the integrity (adversarial examples, poisoning, backdoors) and privacy (reconstruction of training data) of data.
-
The use of artificial intelligence to strengthen cybersecurity (supervision, log analysis, pentesting guided by AI …).
-
The malicious use of generative artificial intelligence (deepfakes detection, traceability of generated data, LLM jailbreaking).
Participants will attend presentations given by national and international researchers whose work has been accepted at leading artificial intelligence and security conferences.
This deliberately interdisciplinary symposium will highlight a variety of fields of application, covering, among other topics, the challenges of artificial intelligence applied to defense, healthcare, or the media. It offers participants a more complete and diversified understanding of the challenges and opportunities in these areas.
PROGRAM
Session #1: AI for Cybersecurity
Wednesday, November 20th – 13:30-18:00 – Room Le Carré 1
-
Fault Injection and Safe-Error Attack for Extraction of Embedded Neural Network Models, Kevin Hector, Pierre-Alain Moëllic, Jean-Max Dutertre, Mathieu Dumont – ESORICS, 2023
-
When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence, Benoît Coqueret, Mathieu Carbone, Olivier Sentieys, Gabriel Zaid – AISEC, 2023
-
Decoding the Secrets of Machine Learning in Malware Classification, Savino Dambra, Yufei Han, Simone Aonzo, Platon Kotzias, Antonino Vitale, Juan Caballero, Davide Balzarotti, Leyla Bilge – SIGSAC, 2023
-
Dos and don’ts of machine learning in computer security, Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro, Konrad Rieck – USENIX Security Symposium, 2022
-
How machine learning is solving the binary function similarity problem, Andrea Marcelli, Mariano Graziano, Xabier Ugarte-Pedrero, Yanick Fratantonio, Mohamad Mansouri, Davide Balzarotti – USENIX Security Symposium, 2022
-
Getting pwn’d by AI : Penetration testing with large language models, Andreas Happe, Jürgen Cito – ESEC/FSE, 2023. presented by Manuel Reinsperger
Session #2: Vulnerabilities of AI
Thrusday, November 21st – 9:00-12:00 – Room La Nef
-
SECURITYNET: Assessing Machine Learning Vulnerabilities on Public Models, Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang – USENIX Security Symposium, 2024
-
On the Privacy-Robustness-Utility Trilemma in Distributed Learning, Youssef Allouah, Rachid Guerraoui, Nirupam Gupta, Rafaël Pinot, John Stephan – ICML, 2023
-
Unveiling the Threat: Investigating Distributed and Centralized Backdoor Attacks in Federated Graph Neural NetworksDigital Threats, Jing Xu, Stefanos Koffas, Stjepan Picek – Digital Threats: Research and Practice, 2024
-
“Real Attackers Don’t Compute Gradients”: Bridging the Gap Between Adversarial ML Research and Practice, Giovanni Apruzzese, Hyrum S. Anderson, Savino Dambra, David Freeman, Fabio Pierazzi, Kevin Roundy – SaTML, 2023
-
When Your AI Becomes a Target: AI Security Incidents and Best Practices, Kathrin Grosse, Lukas Bieringer, Tarek R. Besold, Battista Biggio, Alexandre Alahi – AAAI, 2024
Session #3: GenAI and Security
Thrusday, November 21st – 13:30-18:00 – Room La Nef
-
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models, Hossein Hajipour,
Keno Hassler, Thorsten Holz, Lea Schönherr, Mario Fritz – SaTML, 2024 -
Stealing Part of a Production Language Model, Nicholas Carlini, Daniel Paleka, Krishnamurthy (Dj) Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr – ICML, 2024
-
Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection, Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz – AISec, 2023
-
The Stable Signature: Rooting Watermarks in Latent Diffusion Models, Pierre Fernandez, Guillaume Couairon, Hervé Jégou, Matthijs Douze, Teddy Furon – ICCV, 2023.