most citedMAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Kaiyan Wen, Shijie Zhang, Lu Yu +1

Text-to-image (T2I) models remain vulnerable to jailbreak attacks that elicit Not-Safe-For-Work (NSFW) content, despite increasingly being guarded by heterogeneous, multi-layer saf…