arXiv AI September 2, 2026 By Kaiyan Wen, Shijie Zhang, Lu Yu, Guangdong Bai

Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent Debate

The paper introduces the Detection Surface, a geometric framework that maps the decision boundaries of heterogeneous safety filters in text‑to‑image models. Using this insight, the authors propose CRACK, a multi‑agent debate system that iteratively mutates prompts, diagnoses layer‑specific constraints, and refines attacks to bypass composite defenses. Experiments demonstrate that CRACK can achieve attack success rates up to 99.63% while using fewer queries and preserving semantic fidelity.

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 AI.

arXiv AI

Jul 21

Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

arXiv:2607. 17779v1 Announce Type: new Abstract: Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly in generating Not-Safe-For-Work (NSFW) images.

By Dongdong Yang, Deyue Zhang, Zhao Liu, Zonghao Ying, Wenzhuo Xu, Jiankai Jin, Xiangzheng Zhang, Quanchen Zou

llms diffusion multimodal benchmarks safety

arXiv AI

Aug 19

Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

The paper introduces MemJack, a memory‑augmented multi‑agent framework that automatically generates jailbreak attacks on Vision‑Language Models (VLMs) using benign natural images as visual anchors. MemJack discovers visual anchors, camouflages them semantically, evaluates responses, repairs via reflection, and replans dynamically, forming a closed‑loop attack pipeline. The authors also create MemJack‑Bench, a dataset of over 113,000 interactive multimodal jailbreak trajectories, and show that MemJack achieves a 71.48% attack success rate against Qwen3‑VL‑Plus, reaching 90% under extended budgets, outperforming other baselines on natural‑image evaluation.

By Jianhao Chen, Haoyang Chen, Hanjie Zhao, Haozhe Liang, Zheng Wang, Tieyun Qian

llms agents multimodal safety

arXiv AI

Sep 1

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic...

By Md Rafi Ur Rashid, MD Sadik Hossain Shanto, Vishnu Asutosh Dasu, Shagufta Mehnaz

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv AI

3d ago

SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs

arXiv:2609.38899v1 Announce Type: cross Abstract: Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit poli...

By Wenyu Chen, Li Wang, Chuanchao Zang, Xiangtao Meng, Xinyu Gao, Jianing Wang, Zheng Li, Shanqing Guo

llms multimodal safety

arXiv Computer Vision

Aug 21

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models

arXiv:2604. 05853v3 Announce Type: replace Abstract: Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse.

By Zonghao Ying, Haowen Dai, Lianyu Hu, Zonglei Jing, Quanchen Zou, Yaodong Yang, Aishan Liu, Xianglong Liu

llms diffusion robotics multimodal benchmarks safety

arXiv AI

Jul 21

Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models

arXiv:2607. 17279v1 Announce Type: cross Abstract: Recently, text-to-video (T2V) models have been widely deployed, sparking growing concerns over their robustness against jailbreak attacks.

By Xingkai Peng, Jun Jiang, Jiayang Liu, Kejiang Chen, Weiming Zhang

diffusion safety

One email a morning, machine-written

Related stories

Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models

Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models