VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents
VirusCascade is a stealthy attack targeting LLM-powered recommender systems by exploiting 'collaborative-reflection hijacking.' It jointly manipulates item descriptions (semantic injection) and user interaction paths (structural injection) to make malicious evidence appear as legitimate preferences. This allows the attack to be amplified systemically through the system's own reflection process, achieving high-efficacy targeted promotion stealthily.