Résultats de la recherche - Labunets, Andrey
- Résultat(s) 1 - 5 résultats de 5
-
1
May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks Autoría: Pandya, Nishit V., Labunets, Andrey, Gao, Sicun, Fernandes, Earlence
Publié 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
2
An Empirical Analysis on the Use and Reporting of National Security Letters Autoría: Bellon, Alex, Haller, Miro, Labunets, Andrey, Liu, Enze, Savage, Stefan
Publié 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
3
Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Autoría: Labunets, Andrey, Pandya, Nishit V., Hooda, Ashish, Fu, Xiaohan, Fernandes, Earlence
Publié 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
4
Systems Security Foundations for Agentic Computing Autoría: Christodorescu, Mihai, Fernandes, Earlence, Hooda, Ashish, Jha, Somesh, Rehberger, Johann, Chaudhuri, Kamalika, Fu, Xiaohan, Shams, Khawaja, Amir, Guy, Choi, Jihye, Choudhary, Sarthak, Palumbo, Nils, Labunets, Andrey, Pandya, Nishit V.
Publié 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
5
Agent Security is a Systems Problem Autoría: Christodorescu, Mihai, Fernandes, Earlence, Hooda, Ashish, Jha, Somesh, Rehberger, Johann, Chaudhuri, Kamalika, Fu, Xiaohan, Shams, Khawaja, Amir, Guy, Choi, Jihye, Choudhary, Sarthak, Palumbo, Nils, Labunets, Andrey, Pandya, Nishit V.
Publié 2026Fuente: arXivTipo de material: PreprintAcceso al recurso