SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

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 safety stacks combining text filters, image classifiers, and cross-modal detectors. Existing jailbreak studies either optimize against individual filters or query the complete pipeline with aggregate feedback, making it difficult to identify the active constraint and adapt to conflicts across safety layers. In this paper, we introduce the Detection Surface, a unified geometric framework that characterizes the decision b

Read original source ↗ Open in workspace

recordType

paper

region

Global