Lukianov Kirill Sergeevich

Publications in Math-Net.Ru

1. Securing deep classification models against OOD inputs and evasion attacs
   
   Uspekhi Mat. Nauk, 80:6(486) (2025),  187–190
2. Knowledge distillation in local-region for black-box adversarial examples
   
   Proceedings of ISP RAS, 37:4(2) (2025),  133–146
3. Improved search in graph AutoML: expansion and dynamic prioritization in the search space for enhanced efficiency
   
   Proceedings of ISP RAS, 37:2 (2025),  115–128
4. Extrapolation of the Bayesian classifier with an unknown support of the two-class mixture distribution
   
   Uspekhi Mat. Nauk, 79:6(480) (2024),  57–82
5. Is AI interpretability safe: the relationship between interpretability and security of machine learning models
   
   Proceedings of ISP RAS, 36:5 (2024),  127–142
6. The defender's dilemma: are defense methods against different attacks on machine learning models compatible?
   
   Proceedings of ISP RAS, 36:5 (2024),  109–126
7. Detecting and eliminating covariate shifts in data for a more robust HDD failure prediction
   
   Zap. Nauchn. Sem. POMI, 540 (2024),  148–161
8. A study of graph neural networks for link prediction on vulnerability to membership attacks
   
   Zap. Nauchn. Sem. POMI, 530 (2023),  113–127