Rogov Oleg Y.

Publications in Math-Net.Ru

1. HAMSA: hijacking aligned compact models via stealthy automation
   
   Dokl. RAN. Math. Inf. Proc. Upr., 527 (2025),  449–458
2. Tuning LLM in secure code generation
   
   Proceedings of ISP RAS, 37:5 (2025),  111–122
3. Clarispeech: LLM-enhanced speech recognition post-correction
   
   Zap. Nauchn. Sem. POMI, 546 (2025),  223–245
4. UnGAN: machine unlearning strategies through membership inference
   
   Zap. Nauchn. Sem. POMI, 540 (2024),  46–60