Author name cluster

Jérôme Rony

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2025 Conference Paper

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

Antonio Emanuele Cinà
Jérôme Rony
Maura Pintor
Luca Demetrio
Ambra Demontis
Battista Biggio
Ismail Ben Ayed
Fabio Roli

While novel gradient-based attacks are continuously proposed to improve the optimization of adversarial examples, each is shown to outperform its predecessors using different experimental setups, implementations, and computational budgets, leading to biased and unfair comparisons. In this work, we overcome this issue by proposing AttackBench, i.e., an attack evaluation framework that evaluates the effectiveness of each attack (along with its different library implementations) under the same maximum available computational budget. To this end, we (i) define a novel optimality metric that quantifies how close each attack is to the optimal solution (empirically estimated by ensembling all attacks), and (ii) limit the maximum number of forward and backward queries that each attack can execute on the target model. Our extensive experimental analysis compares more than 100 attack implementations over 800 different configurations, considering both CIFAR-10 and ImageNet models, and shows that only a few attack implementations outperform all the remaining approaches. These findings suggest that novel defenses should be evaluated against different attacks than those normally used in the literature to avoid overly-optimistic robustness evaluations. We release AttackBench as a publicly-available benchmark that will be continuously updated with new attack implementations to maintain an up-to-date ranking of the best gradient-based attacks. We release AttackBench as a publicly available benchmark, including a continuously updated leaderboard and source code to maintain an up-to-date ranking of the best gradient-based attacks.

PDF Details DOI

TMLR Journal 2024 Journal Article

Training Graph Neural Networks Subject to a Tight Lipschitz Constraint

Simona Ioana Juvina
Ana Antonia Neacșu
Jérôme Rony
Jean-Christophe Pesquet
Corneliu Burileanu
Ismail Ben Ayed

We propose a strategy for training a wide range of graph neural networks (GNNs) under tight Lipschitz bound constraints. Specifically, by leveraging graph spectral theory, we derive computationally tractable expressions of a tight Lipschitz constant. This allows us to propose a constrained-optimization approach to control the constant, ensuring robustness to adversarial perturbations. Unlike the existing methods for controlling the Lipschitz constant, our approach reduces the size of the handled matrices by a factor equal to the square of the number of nodes in the graph. We employ a stochastic projected subgradient algorithm, which operates in a block-coordinate manner, with the projection step performed via an accelerated iterative proximal algorithm. We focus on defending against attacks that perturb features while keeping the topology of the graph constant. This contrasts with most of the existing defenses, which tackle perturbations of the graph structure. We report experiments on various datasets in the context of node classification tasks, showing the effectiveness of our constrained GNN model.

PDF Details

NeurIPS Conference 2020 Conference Paper

Information Maximization for Few-Shot Learning

Malik Boudiaf
Imtiaz Ziko
Jérôme Rony
Jose Dolz
Pablo Piantanida
Ismail Ben Ayed

We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based on the support set. Furthermore, we propose a new alternating-direction solver for our mutual-information loss, which substantially speeds up transductive inference convergence over gradient-based optimization, while yielding similar accuracy. TIM inference is modular: it can be used on top of any base-training feature extractor. Following standard transductive few-shot settings, our comprehensive experiments demonstrate that TIM outperforms state-of-the-art methods significantly across various datasets and networks, while used on top of a fixed feature extractor trained with simple cross-entropy on the base classes, without resorting to complex meta-learning schemes. It consistently brings between 2% and 5% improvement in accuracy over the best performing method, not only on all the well-established few-shot benchmarks but also on more challenging scenarios, with domain shifts and larger numbers of classes.

PDF Details