ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models
cs.AI
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/meta-llama/PurpleLlama
Terminology
Sources
- Refusal in Language Models Is Mediated by a Single Direction
- Constitutional AI: Harmlessness from AI Feedback
- Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
- The Structural Safety Generalization Problem
- Are aligned neural networks adversarially aligned?
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
- Jailbreaking Black Box Large Language Models in Twenty Queries
- garak: A Framework for Security Probing Large Language Models
- BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- Gemma 3 Technical Report
- AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
- FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- DeepInception: Hypnotize Large Language Model to Be Jailbreaker
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection