Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
Paper
• 2602.15671 • Published
• 1
Haodong Zhao
billhdzhao
AI & ML interests
Federated Learning, LLM, Agent, Security
Recent Activity
authored
a paper
8 days ago
Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent
Communities authored
a paper
8 days ago
Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning authored
a paper
8 days ago
Judge Before Answer: Can MLLM Discern the False Premise in Question? Organizations
upvoted a paper 8 days ago
upvoted 3 papers 3 months ago
Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
Paper
• 2512.06899 • Published
• 3
PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
Paper
• 2512.02589 • Published
• 72
Latent Collaboration in Multi-Agent Systems
Paper
• 2511.20639 • Published
• 122
upvoted a paper 5 months ago
upvoted a paper 10 months ago