影响力指数

14.06/100

超过 43%

全站排名 #36,665

发表论文6 篇

平均评分5.0

年均产出3.0 篇/年

Chong Xiang

Researcher@NVIDIA·美国·OpenReview

研究方向

AI Security

HieraSuite: A Holistic Toolkit for Building Versatile System-User Instruction Hierarchy

ICLR 2026Rejected

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

ICLR 2026Rejected

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis

ICLR 2026Rejected

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search

NeurIPS 2025Poster

Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

ICLR 2025Poster

Certifiably Robust RAG against Retrieval Corruption Attacks

ICLR 2025Rejected

合作者 (20)

博士导师3 篇

Aleksandra Korolova

Basileal Yoseph Imana