3 papers
cs.CV2026
BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder
Siquan Huang, Yijiang Li, Ningzhi Gao +3
Self-supervised and multimodal vision encoders learn strong visual representations that are widely adopted in downstream vision tasks and large vision-language models (LVLMs). Howe…
cs.CV2024
Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation
Yijiang Li, Sucheng Ren, Weipeng Deng +4
Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains tha…
cs.LG2023
Towards Understanding Adversarial Transferability in Federated Learning
Yijiang Li, Ying Gao, Haohan Wang
We investigate a specific security risk in FL: a group of malicious clients has impacted the model during training by disguising their identities and acting as benign clients but l…