Hugging Face Trending Papers July 7, 2026

AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models

Read the original on Hugging Face Trending Papers →

Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 2

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.

By Yiwei Chen, Yuguang Yao, Yihua Zhang, Bingquan Shen, Gaowen Liu, Sijia Liu

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 29

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models

arXiv:2602. 10179v2 Announce Type: replace-cross Abstract: Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual inputs such as marks, arrows, and visual-text prompts.

By Jiacheng Hou, Yining Sun, Ruochong Jin, Haochen Han, Fangming Liu, Wai Kin Victor Chan, Alex Jinpeng Wang

llms multimodal benchmarks safety

Hugging Face Trending Papers

Jun 24

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as arrows, sketches, and emojis orchestrate complex video dynamics with unprecedented controllability. However, these seemingly innocuous static cues can be interpreted by models as executable temporal instructions, unfolding into harmful actions in the generated videos.

rag diffusion multimodal benchmarks safety

arXiv Machine Learning

Jun 9

What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks

arXiv:2606. 09700v1 Announce Type: cross Abstract: Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content.

By Qin Yang, Lu Malloy, Joshua Lee, Xiaohan Chang, Meisam Mohammady, Doowon Kim, Yuan Hong

llms benchmarks safety

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 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

llms multimodal safety

Related stories

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks

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

Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks