Publications associées à Contrôle d'accès obligatoire

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

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Alexander Carl Unnervik

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

EPFL2024

On the Theory and Practice of Modern Secure Messaging

Daniel Patrick Collins

Billions of people now have conversations daily over the Internet. A large portion of this communication takes place via secure messaging protocols that offer "end-to-end encryption'" guarantees and resilience to compromise like the widely-used Double Ratc ...

EPFL2024

SecureCells: A Secure Compartmentalized Architecture

Babak Falsafi, Mathias Josef Payer, Yuanlong Li, Andrés Sánchez Marín, Florian Hofhammer, Siddharth Gupta, Atri Bhattacharyya

Modern programs are monolithic, combining code of varied provenance without isolation, all the while running on network-connected devices. A vulnerability in any component may compromise code and data of all other components. Compartmentalization separates ...

2023

An anomaly detection approach for backdoored neural networks: face recognition as a case study

Sébastien Marcel, Alexander Carl Unnervik

Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker. Given how steal ...

IEEE2022

Are GAN-based Morphs Threatening Face Recognition?

Sébastien Marcel, Eklavya Sarkar, Laurent Colbois

Morphing attacks are a threat to biometric systems where the biometric reference in an identity document can be altered. This form of attack presents an important issue in applications relying on identity documents such as border security or access control ...

IEEE2022

N-Terminal Selective C-H Azidation of Proline-Containing Peptides: a Platform for Late-Stage Diversification

Jérôme Waser, Raphaël Michel Henri Simonet-Davin, Emmanuelle Madeline Dominique Allouche

A methodology for the C-H azidation of N-terminal proline-containing peptides was developed employing only commercially available reagents. Peptides bearing a broad range of functionalities and containing up to 6 amino acids were selectively azidated at th ...

2022

Depth Camera and Electromagnetic Field Localization System For IoT Application - High level, lightweight data fusion

Yves Perriard, Alexis Boegli, Pooneh Mohaghegh, Rabia Saeed

This article demonstrates person localization using a hybrid system consisting of an electromagnetic positioning system and a depth camera to authorize access control. The ultimate aim of this system is to distinguish moving people in a defined area by tra ...

Association for Computing Machinery2021

BioLocker: A Practical Biometric Authentication Mechanism based on 3D Fingervein

Serge Vaudenay, Loïs Evan Huguenin-Dumittan, Fatma Betül Durak

We design a consecution of protocols which allows organizations to have secure strong access control of their users to their desktop machines based on biometry. It provides both strong secure authentication and privacy. Moreover, our mechanism allows the s ...

Springer, Cham2020

Dynamics and Applications of Dissipative Kerr Solitons

Maxim Karpov

Optical frequency combs are optical sources, which spectrum consists of a series of equally spaced narrowband frequencies. They made an outstanding leap forward in the accuracy of optical frequency metrology and became an attractive tool for numerous appli ...

EPFL2020