Ari Azarafrooz
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1NLP×1ML×1
Research Timeline
2026
Cross-Session Threats in AI Agents: Benchmark, Evaluation, and Algorithms
The paper introduces CSTM-Bench, a comprehensive benchmark and evaluation framework demonstrating that standard session-bound AI guardrails fail against sophisticated, cross-session attacks that accumulate payloads over time.
Highlighted terms show continued research focus across papers