conftrace_

harmful content generation

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

jailbreak attack (7) harmful content (4) large language model (3) safety training (2) llm safety (2) prompt injection (2) adversarial prompt (2) adversarial attack (2) safety alignment (2) model safety (2)

Papers

Jailbreaking? One Step Is Enough! ACL 2025 Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025 SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage ACL 2025 SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models EMNLP 2025 Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models CVPR 2025 A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models ACL 2024 Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs NAACL 2024 Virtual Context Enhancing Jailbreak Attacks with Special Token Injection EMNLP 2024