影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
14.67/100
超过 44.9%
全站排名 #35,499
发表论文5 篇
平均评分
年均产出5.0 篇/年
Jiahao Chen
研究方向
Trustworthy AI · Backdoor Attack · LLM Safety · Agentic Memory
23
STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language Model
ICLR 2026Poster
三作24
Contextual and Seasonal LSTMs for Time Series Anomaly Detection
ICLR 2026Poster
22
Arcueid: Multi-trigger Cloud Shaping for Unified Backdoor Attack Paradigms
ICLR 2026Rejected
二作12
HiddenGuard: Detecting and Interpreting NSFW Prompts in Text-to-Image Models through Uncovering Harmful Semantics
ICLR 2026Withdrawn
二作17
Angel or Demon: Investigating the Plasticity-Enhanced Strategies' Impact on Backdoor Threats in Deep Reinforcement Learning
ICLR 2026Rejected