PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
Viet Pham Ho Chi Minh city University of Science, Vietnam National University, Thai Le Indiana University
原文摘要
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 targeted, compromised responses only for specific queries (e.g., “Who should I vote for the US President?”) while maintaining high utility on benign inputs. Operating in a strict black-box setting without model weight access, PARASITE utilizes a two-stage optimization including a global semantic search followed by a greedy lexical refinement. Tested on open-source models and commercial APIs (GPT-4o-mini, GPT-3.5), PARASITE achieves up to 70% F1 reduction on targeted queries with minimal degradation to general capabilities. We further demonstrate that these poisoned prompts evade standard defenses, including perplexity filters and typo-correction, by exploiting the natural noise found in real-world system prompts.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表