conftrace_

prompt manipulation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

llm jailbreak (1) arabic transliteration (1) unsafe content (1) prompt space (1) disentangled control (1) large language model (1) safety training (1) prompt injection (1) semantic editing (1) cross-attention layer (1)

Papers

An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control AAAI 2025 DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak EMNLP 2025 Jailbreaking LLMs with Arabic Transliteration and Arabizi EMNLP 2024