Publications associées à Attentats du 11 septembre 2001

Machine Learning Security Against Data Poisoning: Are We There Yet?

Poisoning attacks compromise the training data utilized to train machine learning (ML) models, diminishing their overall performance, manipulating predictions on specific test samples, and implanting backdoors. This article thoughtfully explores these atta ...

Ieee Computer Soc2024

Towards more Practical Threat Models in Artificial Intelligence Security

Alexandre Massoud Alahi, Kathrin Grosse

Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI. For example, while models are often studied in isolation, th ...

Usenix Association2024

Distribution Inference Risks: Identifying and Mitigating Sources of Leakage

Robert West, Maxime Jean Julien Peyrard, Valentin Hartmann, Léo Nicolas René Meynent

A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In this attack, the ...

IEEE COMPUTER SOC2023

The Role of Hub Neurons in Modulating Cortical Dynamics

Henry Markram, Felix Schürmann, Idan Segev, Oren Amsalem, Eyal Gal, Michael London

Many neurodegenerative diseases are associated with the death of specific neuron types in particular brain regions. What makes the death of specific neuron types particularly harmful for the integrity and dynamics of the respective network is not well unde ...

2021

Analyzing and Protecting Communication Metadata

Ludovic Barman

Most communication systems (e.g., e-mails, instant messengers, VPNs) use encryption to prevent third parties from learning sensitive information. However, encrypted communications protect the contents but often leak metadata: the amount of data sent and th ...

EPFL2021

Side-Channel Attacks on Threshold Implementations using a Glitch Algebra

Serge Vaudenay

Threshold implementations allow to implement circuits us- ing secret sharing in a way to thwart side-channel attacks based on prob- ing or power analysis. It was proven they resist to attacks based on glitches as well. In this report, we show the limitatio ...

Springer Int Publishing Ag2016

Considerations for Rank-based Cryptosystems

Anna-Lena Horlemann, Joachim Rosenthal

Cryptosystems based on rank metric codes have been considered as an alternative to McEliece cryptosystems due to the relative difficulty of solving the rank syndrome decoding problem. Generic attacks have recently seen several improvements, notably in the ...

Ieee2016

Practical and Provably Secure Distance-Bounding

Serge Vaudenay, Aikaterini Mitrokotsa

From contactless payments to remote car unlocking, many applications are vulnerable to relay attacks. Distance bounding protocols are the main practical countermeasure against these attacks. In this paper, we present a formal analysis of SKI, which recentl ...

IOS Press2015

Motion-Based Counter-Measures to Photo Attacks in Face Recognition

Sébastien Marcel, André Anjos, Murali Mohan Chakka

Identity spoofing is a contender for high-security face recognition applications. With the advent of social media and globalized search, our face images and videos are wide-spread on the internet and can be potentially used to attack biometric systems with ...

2014

Secure & Lightweight Distance-Bounding

Serge Vaudenay, Aikaterini Mitrokotsa, Ioana Cristina Carlson

Distance-bounding is a practical solution to be used in security-sensitive contexts, mainly to prevent relay attacks. The main challenge when designing such protocols is maintaining their inexpensive cryptographic nature, whilst being able to protect again ...

2013