Junyuan Hong

6

Papers

66

Total Citations

Papers (6)

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

Understanding Deep Gradient Leakage via Inversion Influence Functions