698 results
-
Built on sand: on the security of Collaborative Machine Learning
Speaker : Dario Pasquini (EPFL)
This talk is about inaccurate assumptions, unrealistic trust models, and flawed methodologies affecting current collaborative machine learning techniques. In the presentation, we cover different security issues concerning both emerging approaches and well-established solutions in privacy-preserving collaborative machine learning. We start by discussing the inherent insecurity of Split Learning and[…] -
Public Key Encryption with Flexible Pattern Matching
Speaker : Elie Bouscatié - Orange
Many interesting applications of pattern matching (e.g. deep-packet inspection or medical data analysis) target very sensitive data. In particular, spotting illegal behaviour in internet traffic conflicts with legitimate privacy requirements, which usually forces users to blindly trust an entity that fully decrypts their traffic in the name of security. The compromise between traffic analysis and[…] -
Search-Based Local Black-Box Deobfuscation: Understand, Improve and Mitigate
Speaker : Grégoire Menguy (CEA LIST)
Code obfuscation aims at protecting Intellectual Property and other secrets embedded into software from being retrieved. Recent works leverage advances in artificial intelligence (AI) with the hope of getting blackbox deobfuscators completely immune to standard (whitebox) protection mechanisms. While promising, this new field of AI-based, and more specifically search-based blackbox deobfuscation,[…] -
Model Stealing Attacks Against Inductive Graph Neural Networks
Speaker : Yufei Han (INRIA)
Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, the inductive GNNs, which can generalize to unseen data, become mainstream in this direction. Machine learning models have shown great potential in various tasks and have been[…] -
Implémentations sécurisées et évaluation pré-silicium contre les attaques physiques.
Speaker : Sofiane Takarabt
Side-channel attacks remain a permanent threat against embedded systems, thus reliable protections should be implemented and must be minutely evaluated. In this presentation, we study different possible ways to evaluate against such threats. We show how an evaluation can be carried out to validate a security level of a protected hardware implementation. This approach allows us to estimate in[…] -
Security and privacy in personal data management systems
Speaker : Nicolas Anciaux (INRIA)
Personal Data Management Systems (called PDMS) provide individuals with a hardware and/or software solution to manage their data under control. From a data management and security/privacy perspective, the issues involved are complex and differ significantly from the traditional database setting. The emergence of trusted execution environments (such as Intel SGX) could be a game changer. This[…]