conftrace_

defensive strategy

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) personally identifiable information (1) pii leakage (1) security vulnerability (1) privacy threat (1) llm security (1) prompt leakage (1) system prompt (1) data security (1) typographic attack (1)

Papers

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models CVPR 2025 Understanding PII Leakage in Large Language Models: A Systematic Survey IJCAI 2025 Prompt Leakage effect and mitigation strategies for multi-turn LLM Applications EMNLP 2024