影响力指数

27.12/100

前 28%

全站排名 #18,005

发表论文7 篇

平均评分5.4

年均产出2.3 篇/年

Jinghuai Zhang

PhD student@University of California, Los Angeles·美国·OpenReview

研究方向

AI for security · trustworthy machine learning · computer vision

When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

ICLR 2026Poster

MASpi: A Unified Environment for Evaluating Prompt Injection Robustness in LLM-Based Multi-Agent Systems

ICLR 2026Withdrawn

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

ICLR 2025Poster

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

NeurIPS 2025Poster

FoundationForensics: Traceback Backdoor Attacks for Vision Foundation Models

ICLR 2025Withdrawn

合作者 (20)

Neil Zhenqiang Gong