55 results
-
A Fundamental Approach to Cyber Risk Analysis
Speaker : Rainer Böhme (Universität Innsbruck)
This paper provides a framework actuaries can use to think about cyber risk. We propose a differentiated view of cyber versus conventional risk by separating the nature of risk arrival from the target exposed to risk. Our review synthesizes the liter- ature on cyber risk analysis from various disciplines, including computer and network engineering, economics, and actuarial sciences. As a result,[…] -
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[…] -
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[…] -
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[…] -
Towards Security-Oriented Program analysis
Speaker : Sébastien Bardin (CEA LIST)
While digital security concerns increase, we face both a urging demand for more and more code-level security analysis and a shortage of security experts. Hence the need for techniques and tools able to automate part of these code-level security analyses. As source-level program analysis and formal methods for safety-critical applications have made tremendous progress in the past decades, it is[…]