arXiv AI
Jun 6
Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
arXiv:2503. 01734v3 Announce Type: replace-cross Abstract: Attacks on machine learning models have been extensively studied through stateless optimization.
Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning
Related stories
arXiv Machine Learning
Sep 22
Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision
The paper introduces RIBA, a reinforcement‑learning inspired black‑box adversarial attack that generates perturbations for neural networks with fewer queries than existing methods. RIBA achieves a 25.4% reduction in median queries on ResNet‑18/Cifar10 and a 22.5% reduction on Vit‑B/16/ImageNet, while matching white‑box attack performance on an adversarially trained model.
arXiv Machine Learning
Aug 13
Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks
arXiv:2608. 11815v1 Announce Type: new Abstract: Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models.
arXiv Machine Learning
Sep 14
Robust Policy Optimization via Adversarial Importance Sampling
The paper introduces Adversarial Importance Sampling (Advis), a technique that leverages importance sampling over standard training trajectories to estimate and optimize worst‑case returns without extra environment interactions or auxiliary networks, thereby capturing long‑term robustness. It also presents advrl, a modular PyTorch library that consolidates existing robustness methods and adversarial attacks into single‑file implementations for easier prototyping and reproducible evaluation. Finally, the authors highlight that optimal adversarial hyperparameters do not transfer across agents, prompting evaluation against a broader set of attackers (6–14× more configurations) and demonstrate the effectiveness of their approach on continuous control tasks.
arXiv AI
Jun 11
Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization
arXiv:2606. 12251v1 Announce Type: cross Abstract: Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations.
arXiv AI
Sep 2
SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
SEBA is a sample‑efficient framework for black‑box adversarial attacks on visual reinforcement learning agents. It combines a shadow Q model, a generative adversarial network for imperceptible perturbations, and a world model to simulate dynamics, reducing real‑world queries. Experiments on MuJoCo and Atari show SEBA significantly lowers cumulative rewards while preserving visual fidelity and requiring far fewer environment interactions than previous methods.
arXiv Computer Vision
Oct 9
Boosting the Local Invariance for Better Adversarial Transferability
The paper introduces LI-Boost, a technique that enhances the local invariance of adversarial perturbations to improve their transferability across models. By demonstrating a positive correlation between local invariance and transferability, the authors show that LI-Boost significantly boosts five categories of transfer-based attacks on ImageNet, including CNNs, ViTs, defense mechanisms, commercial APIs, and vision-language models. Extensive experiments confirm the method’s effectiveness across diverse architectures and attack types.
arXiv Computer Vision
Oct 1
Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks
arXiv:2605.25663v2 Announce Type: replace-cross Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the featur...
arXiv AI
Jun 10
Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
arXiv:2403. 00420v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments.
arXiv Machine Learning
3d ago
MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition
MIG‑COW is a new adversarial attack framework that uses momentum‑integrated gradients and a consensus‑orthogonal decomposition to create highly generalizable, visually imperceptible perturbations against deepfake detectors. It achieves a 99.96% white‑box attack success rate on the AADD‑2025 Challenge benchmarks while maintaining high perceptual similarity (SSIM). In black‑box settings, its success rate drops to 7.16%, and adding low‑performing but diverse models to the ensemble can reduce attack effectiveness, highlighting the importance of careful surrogate model selection.
arXiv Computer Vision
Sep 10
What Makes Adversarial Examples Transfer Across Deepfake Detectors?
arXiv:2609.10002v1 Announce Type: new Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and t...
arXiv Machine Learning
Oct 5
Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems
arXiv:2602.16543v2 Announce Type: replace Abstract: Safe reinforcement learning (Safe RL) learns robotic controllers that optimize task rewards under safety constraints, yet observation perturbations...