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.
By Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Yi Feng, Xiao Luo, Zijian Xiao, Haowen Xu, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita
The paper presents a preprocessor that recovers and decodes encoded content in vision‑language models to close the decode gap that allows harmful requests to bypass safety classifiers. Evaluated against eleven encoding attacks, the preprocessor raises block rates from 0 % to 67‑90 % but also increases benign over‑refusal, and no configuration achieves an ensemble attack‑success rate below 40 % while keeping benign over‑refusal under 70 %. The study shows that closing one encoding channel merely relocates success rather than eliminating it, highlighting the limits of recovery‑based defenses.
By Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Hanwen Liu, Yi Feng, Haowen Xu, Xiangchen Guan, Yang Chen, Zijian Xiao, Xiao Luo, Mohammad Zandsalimy, Shanu Sushmita
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: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
The paper demonstrates that a targeted adversarial perturbation can reduce a vision‑language model’s training loss to near zero for a fixed target caption, yet the same model, when generating freely, still produces the correct description. This phenomenon, termed the train/inference gap, is traced to a single autoregressive step where the target token’s rank is fixed across all images, and further analysis shows that the language decoder, rather than the visual encoder, determines whether the corrupted signal is amplified or suppressed. The study uses a controlled two‑stage PGD attack on Qwen2.5‑VL‑7B‑Instruct and evaluates the effect on 200 held‑out COCO images, revealing that adversarial robustness in autoregressive VLMs largely depends on the language decoder’s prior.
whyItMatters":"The findings suggest that defenses and faithfulness evaluations for deployed vision‑language models should focus on the language decoder rather than the visual encoder, as the former is the key determinant of robustness to adversarial perturbations."
By Arun Josephraj Arokiaraj, Zekun Wu, Adriano Koshiyama
arXiv:2609. 09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services.
By Viet K. Nguyen, Mohammad I. Husain
The paper introduces Meta-Adaptive Multimodal Jailbreaking (MAMJ), a method that jointly optimizes an attack strategy prompt and attacker weights to generate more effective jailbreaks against vision‑language models. Using an LLM‑based critique to refine the strategy and group‑level success‑rate rewards to update the weights, MAMJ achieves high attack success rates on MM‑SafetyBench, outperforming existing baselines by up to 24.1 percentage points. The learned attacker also transfers to unseen models and remains robust against typical defenses, highlighting a systemic vulnerability in current VLMs.
By Benlei Cui, Shen Pang, Yuke Wang, Xuemei Dong, Yuwen Zhai, Jingqun Tang, Haiyang Yu, Hui Xue, Longtao Huang, Haiwen Hong
arXiv:2610.00024v1 Announce Type: new
Abstract: Across three vision-language model architectures (LLaVA-1.5-7B, Qwen2.5-VL-7B, InternVL3-8B), we report a universal negative finding for mid-layer inte...
By Genpei Zhang
arXiv:2607. 21401v1 Announce Type: cross Abstract: A vision-language AI assistant returns its answer as a stream of generated tokens.
By Dongbin Na
arXiv:2604. 06247v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are vulnerable to jailbreaks and prompt injections delivered through text or images.
By Guy Azov, Ofer Rivlin, Guy Shtar
The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image...
arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.
By Subhadip Mitra