6 papers
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
Hyeonjeong Ha, Qiusi Zhan, Jeonghwan Kim +6
Retrieval-augmented generation (RAG) has become a common practice in multimodal large language models (MLLM) to enhance factual grounding and reduce hallucination. Yet, its relianc…
Securing Multimodal AI through Internal Information Decomposition
Jehyeok Yeon, Hyeonjeong Ha, Qiusi Zhan +1
Multimodal large language models introduce attack surfaces absent in unimodal systems: adversaries can distribute malicious intent across modalities to evade unimodal safeguards. T…
SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents
Qiusi Zhan, Angeline Budiman-Chan, Abdelrahman Zayed +3
Large language model (LLM) based search agents iteratively generate queries, retrieve external information, and reason to answer open-domain questions. While researchers have prima…
BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
Qiusi Zhan, Hyeonjeong Ha, Rui Yang +7
Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. How…
Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
Yuxuan Zhu, Antony Kellermann, Akul Gupta +4
LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when give…
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
Qiusi Zhan, Richard Fang, Henil Shalin Panchal +1
Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external to…