Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Sultan Zavrak

Sultan Zavrak

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1AI×1ML×1

Research Timeline

2026
Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols

The paper proposes a graph-based framework for detecting attacks in LLM agent tool-call traffic, finding that content-level embeddings are crucial for high accuracy and that tree ensembles on these embeddings outperform complex GNN architectures.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.LGRecentMay 11, 2026

Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols

Sultan Zavrak

The paper proposes a graph-based framework for detecting attacks in LLM agent tool-call traffic, finding that content-level embeddings are crucial for high accuracy and that tree ensembles on these em…

View →