arXiv AI September 2, 2026 By Tairan Huang, Yulin Jin, Junxu Liu, Qingqing Ye, Haibo Hu

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

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.

By Kyle Domico, Jean-Charles Noirot Ferrand, Ryan Sheatsley, Eric Pauley, Josiah Hanna, Patrick McDaniel

agents computer-vision reinforcement-learning benchmarks safety

arXiv Machine Learning

1d ago

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.

By Florian Krone, Elena Hoemann, Sven Hallerbach

llms computer-vision reinforcement-learning safety

arXiv AI

Aug 12

Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models

arXiv:2608. 10393v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks.

By Jiahui Han, Yuhui Yao, Xin Wang, Jiafei Cao, Mingxuan Zhang, Danfeng Shan, Huiqi Deng, Guanchu Wang, Xia Hu

diffusion robotics multimodal safety

arXiv AI

Jul 14

AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation

arXiv:2607. 11063v1 Announce Type: new Abstract: Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances.

By Chenyang Li, Kaige Li, Zeyu Jiang, Changhao Chen

llms agents robotics multimodal safety

arXiv AI

Jun 2

Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention

arXiv:2512. 10414v2 Announce Type: replace Abstract: Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs).

By Yang Yu, Zhuangzhuang Chen, Lanqing Li, Xiaomeng Li

llms reinforcement-learning fine-tuning multimodal safety

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.

By Xinhai Zou, Chang Zhao, Alireza Aghabagherloo, Dave Singel\'ee, Robin Degraeve, Bart Preneel

reinforcement-learning safety

One email a morning, machine-written

Related stories

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision

Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models

AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation

Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization