conftrace_

llm jailbreak

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

prompt manipulation (1) safety generalization (1) semantic equivalence (1) red teaming (1) diffusion model (1) adversarial attack (1) text generation (1)

Papers

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak EMNLP 2025 The Structural Safety Generalization Problem ACL 2025