Skip to content
conftrace_

greedy coordinate gradient

3 papers

Explore in graph

Also known as

GCG

Co-occurring keywords · papers mentioning both

large language model (3) adversarial attack (2) probe sampling (1) adversarial suffix (1) llm alignment (1) llm safety (1) red teaming (1) prompt optimization (1) jailbreak attack (1) model alignment (1)

Papers

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models ICLR 2025 Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling NeurIPS 2024 Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models EMNLP 2024