Chen Qian

The paper introduces PriceBlind, a white-box adversarial attack framework that demonstrates how imperceptible visual perturbations can trick multimodal agents into ignoring textual price constraints during financial transactions.

This paper introduces 'Visual Inception,' a novel attack that poisons long-term memory in agentic recommender systems using images, and proposes CognitiveGuard, a dual-process defense framework to mitigate this threat.

SilentRetrieval introduces a sophisticated, two-stage data poisoning attack that successfully hijacks Retrieval-Augmented Generation (RAG) systems by injecting adversarially crafted, yet highly fluent, documents into the retrieval corpus.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.