activity
20222025
most citedA Four-Pronged Defense Against Byzantine Attacks in Federated Learning

26 citations · 42 across the 19 of their papers we have counts for

collaborators

19 papers

cs.LG2025

Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning

Peijin Guo, Minghui Li, Hewen Pan +6

Accurate prediction of molecular metabolic stability (MS) is critical for drug research and development but remains challenging due to the complex interplay of molecular interactio…

cs.CR2025

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

Lei Yu, Yechao Zhang, Ziqi Zhou +6

With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate ina…

cs.LG2025

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets

Yechao Zhang, Yuxuan Zhou, Tianyu Li +4

Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks. However, this combination of…

cs.LG2025

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization

Yechao Zhang, Yingzhe Xu, Junyu Shi +4

Deep neural networks (DNNs) are susceptible to universal adversarial perturbations (UAPs). These perturbations are meticulously designed to fool the target model universally across…

cs.CL2025

Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks

Xiaomei Zhang, Zhaoxi Zhang, Yanjun Zhang +4

Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from t…

cs.LG2025

Multi-Modality Representation Learning for Antibody-Antigen Interactions Prediction

Peijin Guo, Minghui Li, Hewen Pan +6

While deep learning models play a crucial role in predicting antibody-antigen interactions (AAI), the scarcity of publicly available sequence-structure pairings constrains their ge…