Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Volkov, Dmitrii A."'
We saturate a high-school-level hacking benchmark with plain LLM agent design. Concretely, we obtain 95% performance on InterCode-CTF, a popular offensive security benchmark, using prompting, tool use, and multiple attempts. This beats prior work by
Externí odkaz:
http://arxiv.org/abs/2412.02776
Autor:
Reworr, Volkov, Dmitrii
We introduce the LLM Honeypot, a system for monitoring autonomous AI hacking agents. We deployed a customized SSH honeypot and applied prompt injections with temporal analysis to identify LLM-based agents among attackers. Over a trial run of a few we
Externí odkaz:
http://arxiv.org/abs/2410.13919
Autor:
Volkov, Dmitrii
We show that extensive LLM safety fine-tuning is easily subverted when an attacker has access to model weights. We evaluate three state-of-the-art fine-tuning methods-QLoRA, ReFT, and Ortho-and show how algorithmic advances enable constant jailbreaki
Externí odkaz:
http://arxiv.org/abs/2407.01376
Publikováno v:
AIP Conference Proceedings; 2022, Vol. 2509 Issue 1, p1-4, 4p
Publikováno v:
AIP Conference Proceedings Online; April 2022, Vol. 2509 Issue: 1 p020021-20024, 4p
Attosecond Nanotechnology: Quantum Dots of Nanoelectromechanical Systems of CuInx Ga1-x Se2 Compounds.
Autor:
Beznosyuk, Sergey A., Terentyeva, Yulia V., Maslova, Olga A., Zhukovsky, Mark S., Volkov, Dmitrii A.
Publikováno v:
AIP Conference Proceedings; 2016, Vol. 1783 Issue 1, p1-5, 5p, 3 Charts, 3 Graphs
Autor:
Beznosyuk, Sergey A.1 (AUTHOR) bsa1953@mail.ru, Terentyeva, Yulia V.1 (AUTHOR) zyv1985@mail.ru, Gaydukova, Anastasiya A.1 (AUTHOR) gaidukova-anastasiya@mail.ru, Volkov, Dmitrii A.1 (AUTHOR) Rayozorfest@mail.ru
Publikováno v:
AIP Conference Proceedings. 2022, Vol. 2509 Issue 1, p1-4. 4p.