← Search

Jingyu Peng

2 accepted papers

2025

Stepwise Reasoning Disruption Attack of LLMs

ACL 2025long

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain unexplored, particularly in third-party platforms that facilitate user interactions via APIs. Existing attacks on LLM reasoning are constrained by speci…

2023

Beyond Homophily: Robust Graph Anomaly Detection via Neural Sparsification

IJCAI 2023poster

Recently, graph-based anomaly detection (GAD) has attracted rising attention due to its effectiveness in identifying anomalies in relational and structured data. Unfortunately, the performance of most existing GAD methods suffers from the inherent structural noises of graphs induced by hidden anomal…