Skip to content

Author

Eyal Lenga

We have 2 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

This work formalizes agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to extract, and instantiates KYA, a framework that automates black-box, reconnaissance-driven pentesting by probing agents, building target profiles, and using those profiles to craft stronger attacks.

O. Eliav, Eyal Lenga, Shir Bernstien et al. · 0 citations
Open access Jul 2026

Boundary Sampling for Efficient Model Extraction

This work proposes a novel data-free model extraction attack that substantially outperforms current methods in efficiency, accuracy, and overall effectiveness and offers extensions to the algorithm to enable it to work on complex models.

Doron Ben Chayim, Maor Biton Dor, Eyal Lenga et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.