arXiv AI June 9, 2026 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)

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

Read the original on arXiv AI →

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.

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

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

Jun 11

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.

By Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst

llms rag diffusion multimodal 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

Aug 10

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

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.

By Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando, Harshala Gammulle, Basura Fernando, Sanka Rasnayake, A V Subramanyam, Sridha Sridharan, Clinton Fookes

llms computer-vision benchmarks safety

Hugging Face Trending Papers

Jun 2

Investigating Adversarial Robustness of Multi-modal Large Language Models

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.

llms rag fine-tuning multimodal safety

arXiv Machine Learning

Jun 4

Vision Transformer Finetuning Benefits from Non-Smooth Components

arXiv:2602. 06883v3 Announce Type: replace Abstract: The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness.

By Ambroise Odonnat, Laetitia Chapel, Romain Tavenard, Ievgen Redko

llms computer-vision fine-tuning safety

Related stories

Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

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

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

Investigating Adversarial Robustness of Multi-modal Large Language Models

Vision Transformer Finetuning Benefits from Non-Smooth Components