arXiv AI

Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks

arXiv:2607. 26574v2 Announce Type: replace-cross Abstract: Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a classical language, code, or text rendered inside an image slips past a guard that would block it in plain language - the decode gap.

arXiv Machine Learning
Jul 30

Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks

arXiv:2607. 26574v1 Announce Type: cross Abstract: Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet they judge an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a rare language, code, or an image of text slips past a guard that would block it in plain language -- the decode gap.

By Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Zijian Xiao, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita
arXiv AI
Aug 11

Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks

arXiv:2608. 01043v2 Announce Type: replace-cross Abstract: We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR).

By Haoyu Zhang, Xiangchen Guan, Shibo Zheng, Mohammad Zandsalimy, Shanu Sushmita
Hugging Face Trending Papers
Jul 29

Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses

A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate. We show it can be breached by composing two attacks that are individually harmless against it: an established code-completion encoding and an established best-of-N search, neither of which exceeds 4.

arXiv AI
Jun 30

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization

arXiv:2605. 10764v3 Announce Type: replace-cross Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks.

By Mengqi He, Xinyu Tian, Xin Shen, Shu Zou, Jinhong Ni, Zhaoyuan Yang, Weikang Li, Xuesong Li, Jing Zhang
arXiv AI
22h ago

DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization

arXiv:2608. 17067v1 Announce Type: new Abstract: As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and nudity, further exacerbated by red-teaming adversarial attacks.

By Tong Zhang, Motasem Alfarra, Carlos Hinojosa, Christos Louizos, Bernard Ghanem
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