Publications associées à International security

When Your AI Becomes a Target: AI Security Incidents and Best Practices

In contrast to vast academic efforts to study AI security, few real-world reports of AI security incidents exist. Released incidents prevent a thorough investigation of the attackers' motives, as crucial information about the company and AI application is ...

AAAI Press2024

Manipulating Trajectory Prediction with Backdoors

Alexandre Massoud Alahi, Kaouther Messaoud Ben Amor, Kathrin Grosse

Autonomous vehicles ought to predict the surrounding agents' trajectories to allow safe maneuvers in uncertain and complex traffic situations. As companies increasingly apply trajectory prediction in the real world, security becomes a relevant concern. In ...

arXiv2023

On the (In)security of Peer-to-Peer Decentralized Machine Learning

Carmela González Troncoso, Mathilde Aliénor Raynal, Dario Pasquini

In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning-a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both passive and ...

IEEE COMPUTER SOC2023

Effective know-your-customer method for secure and trustworthy non-fungible tokens in media assets

Touradj Ebrahimi, Clément Sanh

Non-fungible tokens (NFTs) are becoming very popular in a large number of applications ranging from copyright protection to monetization of both physical and digital assets. It is however a fact that NFTs suffer from a large number of security issues that ...

SPIE-INT SOC OPTICAL ENGINEERING2022

Security Measures for Grids Against Rank-1 Undetectable Time-Synchronization Attacks

Jean-Yves Le Boudec, Marguerite Marie Nathalie Delcourt

Time-synchronization attacks on phasor measurement units (PMUs) pose a real threat to smart grids; it was shown that they are feasible in practice and that they can have a nonnegligible negative impact on state estimation, without triggering the bad data d ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

PROFACTORY: Improving IoT Security via Formalized Protocol Customization

Mathias Josef Payer, Fei Wang, Duo Xu, Xiangyu Zhang

As IoT applications gain widespread adoption, it becomes important to design and implement IoT protocols with security. Existing research in protocol security reveals that the majority of disclosed protocol vulnerabilities are caused by incorrectly impleme ...

USENIX ASSOC2022

Symmetric Asynchronous Ratcheted Communication with Associated Data

Serge Vaudenay, Hailun Yan

Following up mass surveillance and privacy issues, modern secure communication protocols now seek strong security, such as forward secrecy and post-compromise security, in the face of state exposures. To address this problem, ratcheting was thereby introdu ...

Springer, Cham2020

BenchIoT: A Security Benchmark for the Internet of Things

Mathias Josef Payer

Attacks against IoT systems are increasing at an alarming pace. Many IoT systems are and will be built using low-cost micro-controllers (IoT-pCs). Different security mechanisms have been proposed for IoT-mu Cs with different trade-offs. To guarantee a real ...

IEEE COMPUTER SOC2019

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

International security

When Your AI Becomes a Target: AI Security Incidents and Best Practices

Manipulating Trajectory Prediction with Backdoors

On the (In)security of Peer-to-Peer Decentralized Machine Learning

Effective know-your-customer method for secure and trustworthy non-fungible tokens in media assets

Security Measures for Grids Against Rank-1 Undetectable Time-Synchronization Attacks

PROFACTORY: Improving IoT Security via Formalized Protocol Customization

Symmetric Asynchronous Ratcheted Communication with Associated Data

Numerical back-analysis & future risk assessment of the Hirschigraben landslide(s)

Beyond Conventional Security in Sponge-Based Authenticated Encryption Modes

BenchIoT: A Security Benchmark for the Internet of Things

Graph Chatbot

Chattez avec Graph Search

When Your AI Becomes a Target: AI Security Incidents and Best Practices

Security Measures for Grids Against Rank-1 Undetectable Time-Synchronization Attacks

BenchIoT: A Security Benchmark for the Internet of Things

On the (In)security of Peer-to-Peer Decentralized Machine Learning

Numerical back-analysis & future risk assessment of the Hirschigraben landslide(s)

Manipulating Trajectory Prediction with Backdoors

Effective know-your-customer method for secure and trustworthy non-fungible tokens in media assets

Beyond Conventional Security in Sponge-Based Authenticated Encryption Modes

PROFACTORY: Improving IoT Security via Formalized Protocol Customization

Symmetric Asynchronous Ratcheted Communication with Associated Data