Sultan Zavrak
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
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