RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/whitecircle/rise
Sources
- SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
- Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
- Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
- Harnessing LLM to Attack LLM-Guarded Text-to-Image Models
- Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
- Erasing Concepts from Diffusion Models
- HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
- EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
- Curiosity-driven Red-teaming for Large Language Models
- Perception-guided Jailbreak against Text-to-Image Models
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
- ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
- Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
- AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
- Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
- FLIRT: Feedback Loop In-context Red Teaming
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems