18 citations · 18 across the 2 of their papers we have counts for
4 papers
MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems
Lei Ma, Dennis Hofmann, Haowen Xu +4
Recent studies report that LLM-based multi-agent systems (MAS) fail at rates of 41%-87%, yet to our knowledge, no benchmark to date supports systematic anomaly detection (AD) for t…
Detect, Localize, and Explain: Interactive Hierarchical Log Anomaly Analytics with LLM Augmentation
Lei Ma, Suhani Chaudhary, Ethan Shanbaum +5
Logs are ubiquitous in modern systems. Unfortunately, their unstructured nature in flat sequences limits understanding of execution behaviors, hindering effective anomaly diagnosis…
KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction
Lei Ma, Jinyang Liu, Tieying Zhang +5
Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure i…
Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices
Peter M. VanNostrand, Ioannis Kyriazis, Michelle Cheng +2
Performing deep learning on end-user devices provides fast offline inference results and can help protect the user's privacy. However, running models on untrusted client devices re…