6 papers
From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense
Binyan Xu, Fan Yang, Xilin Dai +2
Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model re…
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
Fan Yang, Binyan Xu, Di Tang +1
GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend on inspecting specific subgraph…
CtrlRAG: Black-box Document Poisoning Attacks for Retrieval-Augmented Generation of Large Language Models
Runqi Sui
Retrieval-Augmented Generation (RAG) systems enhance response credibility and traceability by displaying reference contexts, but this transparency simultaneously introduces a novel…
Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
Binyan Xu, Fan Yang, Di Tang +2
Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications…
CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
Binyan Xu, Fan Yang, Xilin Dai +2
Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on pois…
One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP
Binyan Xu, Xilin Dai, Di Tang +1
Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or…