ArXiv TLDR

Zhan Qin

2 papers · Latest:

Cryptography & Security

Defense against Poisoning Attacks under Shuffle-DP

This paper introduces the first general framework to defend against poisoning attacks in shuffle-DP for all union-preserving queries, ensuring robust privacy and utility.

2605.00625
Cryptography & Security

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models

This paper introduces the Expected Safety Impact (ESI) framework to identify safety-critical parameters in LLMs and proposes targeted intervention methods.

2604.08297

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.