Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems

arXiv:2608.00973 · cs.CL · Submitted 2026-08-02 · Read on arXiv

Wanguang Li, Zhaoxin Wang, Handing Wang

cs.CL

Submitted: 2026-08-02

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generator — 64× in this paper · explained in 2 episodes
• Tokenization — 18× in this paper · explained in 2 episodes
• Evolutionary Search — 16× in this paper · explained in 3 episodes
• Ablation — 11× in this paper · explained in 1 episode
• Surrogate Model — 10× in this paper · explained in 3 episodes
• Filter-Generator Discrepancy — 9× in this paper
• Surrogate Models — 9× in this paper · explained in 3 episodes
• Attack Success Rate — 6× in this paper
• Bypass Rate — 6× in this paper
• Consistency — 6× in this paper · explained in 3 episodes
• Diffusion Model — 6× in this paper · explained in 10 episodes
• Diffusion Models — 6× in this paper · explained in 9 episodes
• Regularization — 6× in this paper · explained in 3 episodes
• Semantic Consistency — 6× in this paper
• Hyperparameters — 5× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Robustness — 3× in this paper · explained in 6 episodes
• Semantic Preservation — 3× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Transformers — 2× in this paper · explained in 2 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Admissibility — 1× in this paper · explained in 2 episodes
• Attack Success Rate (ASR) — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Coherence — 1× in this paper · explained in 2 episodes
• Composition — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Feedback Loop — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Obfuscation — 1× in this paper · explained in 2 episodes
• Overfitting — 1× in this paper · explained in 2 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 6 episodes
• Semantic Equivalence — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 5 episodes

Sources

• Discovering the Hidden Vocabulary of DALLE-2
• Harnessing LLM to Attack LLM-Guarded Text-to-Image Models
• Seedream 3.0 Technical Report
• DiffGuard: Text-Based Safety Checker for Diffusion Models
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Qwen-Image Technical Report
• ShieldGemma: Generative AI Content Moderation Based on Gemma
• Qwen3Guard Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering