Learning diverse attacks on large language models for robust red-teaming and safety tuning

arXiv:2405.18540 · cs.CL, cs.CR, cs.LG · Submitted 2024-05-28 · Read on arXiv

cs.CL, cs.CR, cs.LG

Submitted: 2024-05-28

Updated: 2026-08-31

Code: https://github.com/GFNOrg/red-teaming

Terminology

• Fine-Tuning — 31× in this paper · explained in 5 episodes
• International Conference on Learning Representations — 9× in this paper
• Adaptation — 7× in this paper · explained in 1 episode
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Regularization — 4× in this paper · explained in 3 episodes
• Reward Hacking — 4× in this paper · explained in 8 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Mode Collapse — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• AdamW Optimizer — 2× in this paper · explained in 1 episode
• Bayesian Optimization — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• International Conference on Machine Learning — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Adversarial Training — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• In-Context Learning (ICL) — 1× in this paper · explained in 5 episodes
• Initial Data — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Meta-learning — 1× in this paper · explained in 2 episodes
• National Research Foundation of Korea — 1× in this paper
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Supervised Fine-tuning — 1× in this paper
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Constitutional AI: Harmlessness from AI Feedback
• Jailbreaking Black Box Large Language Models in Twenty Queries
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Baseline Defenses for Adversarial Attacks Against Aligned Language Models
• Mistral 7B
• QGFN: Controllable Greediness with Action Values
• The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
• Investigating Adversarial Trigger Transfer in Large Language Models
• Gemma: Open Models Based on Gemini Research and Technology
• Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
• Equivalence Between Policy Gradients and Soft Q-Learning
• Proximal Policy Optimization Algorithms
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Ethical and social risks of harm from Language Models
• Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling

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