Publication

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

Related publications (54)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

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 ...

arXiv2023

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

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

Sébastien Marcel, Alexander Carl Unnervik

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

Presentation attack detection (PAD) is now considered critically important for any face-recognition (FR) based access-control system. Current deep-learning based PAD systems show excellent performance when they are tested in intra-dataset scenarios. Under ...

IEEE2020

MedChain: Accountable and Auditable Data Sharing in Distributed Medical Scenarios

Jean-Pierre Hubaux, Bryan Alexander Ford, Juan Ramón Troncoso-Pastoriza, Linus Gasser, Jean Louis Raisaro

The current trend towards personalized medicine creates an urgent need to share data among different hospitals and health institutions, which endangers the privacy of the data subjects if not done with the appropriate precautions. Conversely, the frequency ...

2019

BioID: a Privacy-Friendly Identity Document

Serge Vaudenay, Muhammed Fatih Balli, Fatma Betül Durak

We design a suite of protocols so that a small tamper-resistant device can be used as a biometric identity document which can be scanned by authorized terminals. We target both strongly secure identification and strong privacy. Unlike biometric passports, ...

Springer2019

BioID: A Privacy-Friendly Identity Document

Serge Vaudenay, Muhammed Fatih Balli, Fatma Betül Durak

We design a suite of protocols so that a small tamperresistant device can be used as a biometric identity document which can be scanned by authorized terminals. We target both strongly secure identification and strong privacy. Unlike biometric passports, o ...

SPRINGER INTERNATIONAL PUBLISHING AG2019

, ,

Remote Direct Memory Access (RDMA) is becoming widely available in data centers. This technology allows a process to directly read and write the memory of a remote host, with a mechanism to control access permissions. In this paper, we study the fundamenta ...

2019

, ,

The undeniable convenience of face-recognition (FR) based biometrics has made it an attractive tool for access control in various applications, from immigration-control to remote banking. Widespread adopti on of face biometrics, however, depends on the how ...

Springer2019