EUVIMEDEUVIMED entdecken
Crossref

Membership Inference Attacks Against Deep Learning Models via Logits Distribution

Hongyang Yan, Shuhao Li, Yajie Wang, Yaoyuan Zhang, Kashif Sharif, Haibo Hu, Yuanzhang Li

IEEE Transactions on Dependable and Secure Computing · 01.09.2023 · 20 (5) · 3799-3808

DOI: 10.1109/tdsc.2022.3222880 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, erschienen am 01.09.2023. Verfasst von Hongyang Yan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep Learning(DL) techniques have gained significant importance in the recent past due to their vast applications. However, DL is still prone to several attacks, such as the Membership Inference Attack (MIA), based on the memorability of training data. MIA aims at determining the presence of specific data in the training dataset of the model with substitute model of similar structure to the objective model. As MIA relies on the substitute model, they can be mitigated if the substitute model is not clear about the network structure of the objective model. To solve the challenge of shadow-model construction, this work presents L-Leaks, a member inference attack based on Logits. L-Leaks allow an adversary to use the substitute model's information to predict the presence of membership if the shadow and objective model are similar enough. Here, the substitute model is built by learning the logits of the objective model, hence making it similar enough. This results in the substitute model having sufficient confidence in the member samples of the objective model. The evaluation of the attack's success shows that the proposed technique can execute the attack more accurately than existing techniques. It also shows that the proposed MIA is significantly robust under different network models and datasets.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yan, H., Li, S., Wang, Y., Zhang, Y., Sharif, K., Hu, H., & Li, Y. (2023). Membership Inference Attacks Against Deep Learning Models via Logits Distribution. IEEE Transactions on Dependable and Secure Computing, 20(5), 3799-3808. https://doi.org/10.1109/tdsc.2022.3222880

Vancouver

Yan H, Li S, Wang Y, Zhang Y, Sharif K, Hu H, et al. Membership Inference Attacks Against Deep Learning Models via Logits Distribution. IEEE Transactions on Dependable and Secure Computing. 2023;20(5):3799-3808. doi:10.1109/tdsc.2022.3222880

BibTeX
@article{Yan2023,
  author = {Yan, Hongyang and Li, Shuhao and Wang, Yajie and Zhang, Yaoyuan and Sharif, Kashif and Hu, Haibo and Li, Yuanzhang},
  title = {Membership Inference Attacks Against Deep Learning Models via Logits Distribution},
  journal = {IEEE Transactions on Dependable and Secure Computing},
  year = {2023},
  volume = {20},
  number = {5},
  pages = {3799--3808},
  doi = {10.1109/tdsc.2022.3222880}
}
Kostenlos starten →