EUVIMEDEUVIMED entdecken
Crossref

Systemization of Knowledge: Robust Deep Learning using Hardware-software co-design in Centralized and Federated Settings

Ruisi Zhang, Shehzeen Hussain, Huili Chen, Mojan Javaheripi, Farinaz Koushanfar

ACM Transactions on Design Automation of Electronic Systems · 30.11.2023 · 28 (6) · 1-32

DOI: 10.1145/3616868 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 16.10.2023. Verfasst von Ruisi Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 163 Literaturangaben. Gefördert von: Multidisciplinary University Research Initiative, NSF-CNS, NSF TILOS AI institute.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) models are enabling a significant paradigm shift in a diverse range of fields, including natural language processing and computer vision, as well as the design and automation of complex integrated circuits. While the deep models – and optimizations based on them, e.g., Deep Reinforcement Learning (RL) – demonstrate a superior performance and a great capability for automated representation learning, earlier works have revealed the vulnerability of DL to various attacks. The vulnerabilities include adversarial samples, model poisoning, and fault injection attacks. On the one hand, these security threats could divert the behavior of the DL model and lead to incorrect decisions in critical tasks. On the other hand, the susceptibility of DL to potential attacks might thwart trustworthy technology transfer as well as reliable DL deployment. In this work, we investigate the existing defense techniques to protect DL against the above-mentioned security threats. Particularly, we review end-to-end defense schemes for robust deep learning in both centralized and federated learning settings. Our comprehensive taxonomy and horizontal comparisons reveal an important fact that defense strategies developed using DL/software/hardware co-design outperform the DL/software-only counterparts and show how they can achieve very efficient and latency-optimized defenses for real-world applications. We believe our systemization of knowledge sheds light on the promising performance of hardware-software co-design of DL security methodologies and can guide the development of future defenses.

Förderung

  • Multidisciplinary University Research Initiative
  • NSF-CNS
  • NSF TILOS AI institute
  • NSF TrustHub
  • Intelligence Advanced Research Projects Activity (IARPA) TrojAI

Zitieren

APA

Zhang, R., Hussain, S., Chen, H., Javaheripi, M., & Koushanfar, F. (2023). Systemization of Knowledge: Robust Deep Learning using Hardware-software co-design in Centralized and Federated Settings. ACM Transactions on Design Automation of Electronic Systems, 28(6), 1-32. https://doi.org/10.1145/3616868

Vancouver

Zhang R, Hussain S, Chen H, Javaheripi M, Koushanfar F. Systemization of Knowledge: Robust Deep Learning using Hardware-software co-design in Centralized and Federated Settings. ACM Transactions on Design Automation of Electronic Systems. 2023;28(6):1-32. doi:10.1145/3616868

BibTeX
@article{Zhang2023,
  author = {Zhang, Ruisi and Hussain, Shehzeen and Chen, Huili and Javaheripi, Mojan and Koushanfar, Farinaz},
  title = {Systemization of Knowledge: Robust Deep Learning using Hardware-software co-design in Centralized and Federated Settings},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2023},
  volume = {28},
  number = {6},
  pages = {1--32},
  doi = {10.1145/3616868}
}
Kostenlos starten →