Securing deep classification models against OOD inputs and evasion attacs
- Autores: Lukianov K.S.1,2,3, Yaskov P.A.4,5
-
Afiliações:
- Ivannikov Institute for System Programming of the Russian Academy of Sciences
- Moscow Institute of Physics and Technology (National Research University)
- Research Center of the Trusted Artificial Intelligence ISP RAS
- Steklov Mathematical Institute of Russian Academy of Sciences
- National University of Science and Technology "MISIS"
- Edição: Volume 80, Nº 6 (2025)
- Páginas: 187-190
- Seção: МАТЕМАТИЧЕСКИЕ АСПЕКТЫ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА
- URL: https://ogarev-online.ru/0042-1316/article/view/358708
- DOI: https://doi.org/10.4213/rm10290
- ID: 358708
Citar
Resumo
Sobre autores
Kirill Lukianov
Ivannikov Institute for System Programming of the Russian Academy of Sciences; Moscow Institute of Physics and Technology (National Research University); Research Center of the Trusted Artificial Intelligence ISP RAS
Email: lukianov@ispras.ru
Pavel Yaskov
Steklov Mathematical Institute of Russian Academy of Sciences; National University of Science and Technology "MISIS"
Email: yaskov@mi-ras.ru
Scopus Author ID: 36635347000
Researcher ID: S-2745-2016
Candidate of physico-mathematical sciences, no status
Bibliografia
- Shiyu Liang, Yixuan Li, R. Srikant, Enhancing the reliability of out-of-distribution image detection in neural networks, 2020 (v1 – 2017), 15 pp.
- Zhilin Zhao, Longbing Cao, Kun-Yu Lin, IEEE Trans. Neural Netw. Learn. Syst., 35:10 (2024), 13777–13788
- Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, Somesh Jha, Machine learning and knowledge discovery in databases. Research track (ECML PKDD 2021) (Bilbao, 2021), Lecture Notes in Comput. Sci., 12977, Springer, Cham, 2021, 430–445
- Sangwoong Yoon, Jinwon Choi, Yonghyeon Lee, Yung-Kyun Noh, Frank Chongwoo Park, Evaluating out-of-distribution detectors through adversarial generation of outliers, 2022, 17 pp.
- WonJun Moon, Junho Park, Hyun Seok Seong, Cheol-Ho Cho, Jae-Pil Heo, Computer vision – ECCV 2022 (Tel Aviv, 2022), Lecture Notes in Comput. Sci., 13685, Springer, Cham, 2022, 365–381
- A. Madry, A. Makelov, L. Schmidt, D. Tsipras, A. Vladu, Towards deep learning models resistant to adversarial attacks, 2019 (v1 – 2017), 28 pp.
- C. Finlay, A. M. Oberman, Mach. Learn. Appl., 3 (2021), 100017, 8 pp.
- A. Sinha, Zhao Chen, V. Badrinarayanan, A. Rabinovich, Gradient adversarial training of neural networks, 2018, 13 pp.
- D. Jakubovitz, R. Giryes, Computer vision – ECCV 2018 (Munich, 2018), Lecture Notes in Comput. Sci., 11216, Springer, Cham, 2018, 525–541
- Zhihui Zhu, Tianyu Ding, Jinxin Zhou, Xiao Li, Chong You, J. Sulam, Qing Qu, NIPS' 21: Proceedings of the 35th international conference on neural information processing systems, Adv. Neural Inf. Process. Syst., 34, Curran Associates Inc., Red Hook, NY, 2021, 29820–29834
- V. Papyan, X. Y. Han, D. L. Donoho, Proc. Natl. Acad. Sci. USA, 117:40 (2020), 24652–24663
Arquivos suplementares
