← Search

Binyan Xu

2 accepted papers

2026

Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization

AAAI 2026technical

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. A critical flaw in existing methods is that the poison rate required for a successful attack induces a proportional, a

Cited by 7SourcePDFScholar
2026

From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense

ICML 2026poster

Deep Neural Networks (DNNs) remain fundamentally vulnerable to backdoor attacks. Traditional data-free defenses largely operate under the paradigm of internal diagnosis methods like model repairing or input robustness, yet these approaches are often fragile under advanced attacks as they remain enta…

Cited by 0SourceScholar