Risultati della ricerca - Labunets, Andrey

May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks di Pandya, Nishit V., Labunets, Andrey, Gao, Sicun, Fernandes, Earlence

Testo

An Empirical Analysis on the Use and Reporting of National Security Letters di Bellon, Alex, Haller, Miro, Labunets, Andrey, Liu, Enze, Savage, Stefan

Testo

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface di Labunets, Andrey, Pandya, Nishit V., Hooda, Ashish, Fu, Xiaohan, Fernandes, Earlence

Testo

Systems Security Foundations for Agentic Computing di 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.

Testo

Agent Security is a Systems Problem di 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.

Testo