arXiv Machine Learning September 22, 2026 By Florian Krone, Elena Hoemann, Sven Hallerbach

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

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 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...

By Florent Tariolle, Florian Yger

safety

arXiv Machine Learning

Aug 6

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.

By Binyan Xu, Xilin Dai, Di Tang, Kehuan Zhang

llms multimodal safety

arXiv AI

Jul 17

Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks

arXiv:2607. 14921v1 Announce Type: cross Abstract: Machine learning models are increasingly adapted in various domains.

By Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh

benchmarks safety

arXiv Machine Learning

Aug 3

Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations

arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.

By Jun Liu, Leo Yu Zhang, Fengpeng Li, Isao Echizen, Jiantao Zhou

computer-vision benchmarks 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

Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks

Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization