: Can We Trust GenAI Recommendations? Unpacking Adversarial Vulnerabilities in LLM/VLM Ranking Systems
This talk presents a comprehensive analysis of vulnerabilities in modern generative rankers, ranging from atomic attacks to ecosystem-level dynamics, and model the search ecosystem as a game-theoretic dilemma, revealing a "Paradox of Defense" where standard countermeasures may inadvertently incentivize an arms race bet...