9 papers
VisCritic: Visual State Comparison as Process Reward for GUI Agents
Jiachen Qian
GUI agents powered by vision-language models show strong potential for automating digital tasks, yet frequently fail in long-horizon scenarios due to the absence of step-level veri…
JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models
Jiachen Qian
Forensic vision-language models (VLMs) have recently been developed to detect image tampering and provide natural-language explanations. However, their robustness against adversari…
SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
Jiachen Qian
Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning…
Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning
Jiachen Qian
The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks.…
Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations
Jiachen Qian, Zhaolu Kang
The rapid proliferation of Multimodal Large Language Models (MLLMs) has enabled mobile agents to execute high-stakes financial transactions, but their adversarial robustness remain…
How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction
Yingjie He, Zhaolu Kang, Kehan Jiang +17
Large language models (LLMs) excel at semantic understanding, yet their ability to reconstruct internal structure from scrambled inputs remains underexplored. Sentence-level restor…