Search Results for author:
Found 17 papers, 6 papers with code
Under manipulations, are some AI models harder to audit?
Auditors need robust methods to assess the compliance of web platforms with the law.
Fairness Auditing with Multi-Agent Collaboration
We theoretically study their interplay when agents operate independently or collaborate.
On the relevance of APIs facing fairwashed audits
We then simulate practical scenarios in which the auditor may mostly rely on the API to conveniently conduct the audit task, while maintaining her chances to detect a potential manipulation.
FBI: Fingerprinting models with Benign Inputs
We achieve both goals by demonstrating that benign inputs, that are unmodified images, for instance, are sufficient material for both tasks.
Randomized Smoothing under Attack: How Good is it in Pratice?
We first formally highlight the mismatch between a theoretical certification and the practice of attacks on classifiers.
Algorithmic audits of algorithms, and the law
In this paper, we focus on external audits that are conducted by interacting with the user side of the target algorithm, hence considered as a black box.
RoBIC: A benchmark suite for assessing classifiers robustness
Many defenses have emerged with the development of adversarial attacks.
Setting the Record Straighter on Shadow Banning
Shadow banning consists for an online social network in limiting the visibility of some of its users, without them being aware of it.
SurFree: a fast surrogate-free black-box attack
This paper presents SurFree, a geometrical approach that achieves a similar drastic reduction in the amount of queries in the hardest setup: black box decision-based attacks (only the top-1 label is available).
The Bouncer Problem: Challenges to Remote Explainability
The concept of explainability is envisioned to satisfy society's demands for transparency on machine learning decisions.
TamperNN: Efficient Tampering Detection of Deployed Neural Nets
This has a critical impact on the security and reliability of those deployed devices.
MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
A recent technical breakthrough in the domain of machine learning is the discovery and the multiple applications of Generative Adversarial Networks (GANs).
zoNNscan : a boundary-entropy index for zone inspection of neural models
The training of deep neural network classifiers results in decision boundaries which geometry is still not well understood.
Sequences, Items And Latent Links: Recommendation With Consumed Item Packs
In this paper, we introduce the notion of consumed item pack (CIP) which enables to link users (or items) based on their implicit analogous consumption behavior.
Adversarial Frontier Stitching for Remote Neural Network Watermarking
The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements.
Cryptography and Security
The topological face of recommendation: models and application to bias detection
Recommendation plays a key role in e-commerce and in the entertainment industry.
Social and Information Networks Computers and Society Information Retrieval
Distributed deep learning on edge-devices: feasibility via adaptive compression
We report a reduction of the total amount of data sent by workers to the server by two order of magnitude (e. g., 191-fold reduction for a convolutional network on the MNIST dataset), when compared to a standard asynchronous stochastic gradient descent, while preserving model accuracy.
