Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting

arXiv:2411.16769 · cs.LG, cs.CL, cs.CR, cs.CV · Submitted 2024-11-25 · Read on arXiv

cs.LG, cs.CL, cs.CR, cs.CV

Submitted: 2024-11-25

Updated: 2026-09-26

Code: https://github.com/zhiyichin/ICER

Terminology

• Diffusion Model — 17× in this paper · explained in 8 episodes
• Diffusion Models — 16× in this paper · explained in 6 episodes
• Thompson Sampling — 13× in this paper
• Ablation — 11× in this paper · explained in 1 episode
• Consistency — 11× in this paper · explained in 3 episodes
• Perplexity — 10× in this paper · explained in 3 episodes
• In-Context Learning — 8× in this paper · explained in 4 episodes
• Transferability — 7× in this paper · explained in 4 episodes
• Failure Rate — 6× in this paper
• Adversarial Attacks — 5× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Generative Model — 5× in this paper · explained in 2 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Ablation study — 4× in this paper · explained in 1 episode
• Adaptation — 4× in this paper · explained in 1 episode
• Adversarial Training — 4× in this paper · explained in 1 episode
• Bayesian Optimization — 4× in this paper · explained in 3 episodes
• European Conference on Computer Vision — 4× in this paper
• Generative Models — 4× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 4× in this paper
• Reward Function — 4× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• In Association for Computational Linguistics — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Semantic Similarity — 3× in this paper · explained in 2 episodes
• Actor — 2× in this paper · explained in 3 episodes
• Bayesian Inference — 2× in this paper · explained in 5 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Generalizability — 2× in this paper · explained in 6 episodes
• In Empirical Methods in Natural Language Processing — 2× in this paper
• In IEEE Symposium on Security and Privacy — 2× in this paper
• In International Conference on Machine Learning — 2× in this paper
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• alpha — 2× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accountability — 1× in this paper · explained in 2 episodes
• Adaptive Sampling — 1× in this paper · explained in 1 episode
• Agentic Approaches — 1× in this paper · explained in 1 episode
• Algorithmic Improvements — 1× in this paper · explained in 1 episode
• Bayesian Optimization (BO) — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• In Conference on Language Modeling — 1× in this paper
• In-Context Learning (ICL) — 1× in this paper · explained in 5 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes

Sources

• HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Zephyr: Direct Distillation of LM Alignment
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks