arXiv Machine Learning August 10, 2026 By Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando, Harshala Gammulle, Basura Fernando, Sanka Rasnayake, A V Subramanyam, Sridha Sridharan, Clinton Fookes

Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers

Read the original on arXiv Machine Learning →

arXiv:2608. 06674v1 Announce Type: cross Abstract: Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical systems.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 10

Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT

arXiv:2607. 07922v1 Announce Type: cross Abstract: Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.

By Giulia Marchiori Pietrosanti, Giulio Rossolini, Giorgio Buttazzo

llms safety

arXiv AI

Aug 5

Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking

arXiv:2608. 03231v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies promise general robotic manipulation, but their robustness against physical-world attacks remains fragile.

By Jinquan Zhang, Dongfu Yin, Run Yang, Yufeng Yan, Zhen Tian, F. Richard Yu

robotics fine-tuning multimodal safety

arXiv AI

Jun 9

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

arXiv:2606. 07593v1 Announce Type: cross Abstract: The widespread use of image classification models in high-risk, real-world situations necessitates making these models robust to slight disturbances or perturbations, such as blurring or sharpening, in the input images.

By Hannah Gao (Massachusetts Institute of Technology), Isha Agarwal (Massachusetts Institute of Technology), Dylan Hadfield-Menell (Massachusetts Institute of Technology), Rachel Ma (Massachusetts Institute of Technology)

llms computer-vision fine-tuning multimodal safety

arXiv Machine Learning

Jun 26

Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

arXiv:2510. 00586v3 Announce Type: replace Abstract: Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned documents for each target phrase.

By Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen

rag safety

arXiv AI

Jun 10

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.

By Lijia Yu, Jiuxin Cao, Yuchen Qiang, Changhao Chen, Yifei Huang, Bo Liu

llms multimodal safety

arXiv Machine Learning

Jun 30

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.

By Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang

llms multimodal safety

Related stories

Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT

Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models