Bing Chen

LISS: Defending against label inference attacks in VFL via secret subsampling

ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization

ElasticBack is presented, an effective conditional single-skill backdoor that plants a rule R in the skill document and a benign-looking trigger T in the user query, so the malicious payload fires only when both co-occur, and motivates stronger defenses for the skill supply chain.

FedPurify: Knowledge-Preserving Backdoor Defense with Data-Free Purification in Federated Learning

FedPurify is a framework that performs post-training data-free purification to remove malicious backdoors while preserving task-relevant knowledge in FL, and combines contrastive feature alignment with knowledge-preserving self-distillation to remove backdoor effects while preserving benign task performance.

FedPurify: Knowledge-Preserving Backdoor Defense with Data-Free Purification in Federated Learning

Federated Learning (FL) facilitates distributed training while preserving privacy, yet remains highly vulnerable to backdoor attacks. Existing defenses primarily address these threats via robust aggregation, which reduces the influence of malicious contributions (e.g., pruning, reweighting), or through detection-based...