conftrace_

adversarial prompt generation

3 papers

Explore in graph

Co-occurring keywords

large language model (13587) red teaming (61) language model (4599) harmful content detection (54) prompt injection (101) language model security (12) safety optimization (1) jailbreak attack (225) jailbreaking attack (26) black-box attack (237)

Papers

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment ACL 2026
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models AAAI 2025
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically NIPS 2024