← Front PageAI Security Desk
AI Security
PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
PARASITE attack poisons system prompts conditionally to hijack LLMs via supply chain compromise.
Summary written by editorial AI · Source link below
arXiv:2505.16888v4 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed via third-party system prompts downloaded from public marketplaces. We identify a critical supply-chain vulnerability: conditional system prompt poisoning, where an adversary injects a ``sleeper agent'' into a benign-looking prompt. Unlike traditional jailbreaks that aim for broad refusal-breaking, our proposed framework, PARASITE, optimizes system prompts to trigger LLMs to output targete
Continue at the source
Read the full report at arXiv Crypto & SecurityExternal link — opens at arXiv Crypto & Security in a new tab.
§
Continue with
More from the AI Security Desk
- Hugging Face warns an autonomous AI agent hacked its network20 Jul
- Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking20 Jul
- Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior20 Jul
- Poison to Detect: Detection of Targeted Overfitting in Federated Learning20 Jul
- Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation20 Jul