Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks-Reference-Cited by-同舟云学术

Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks

Published:2023-11-15 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security
language:
Short-container-title:

Author:

Feng Ryan¹^ORCID,Hooda Ashish²^ORCID,Mangaokar Neal¹^ORCID,Fawaz Kassem²^ORCID,Jha Somesh²^ORCID,Prakash Atul¹^ORCID

Affiliation:

1. University of Michigan, Ann Arbor, MI, USA

2. University of Wisconsin-Madison, Madison, WI, USA

Funder

Defense Advanced Research Projects Agency

National Science Foundation

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3576915.3623116

Reference46 articles.

1. Amazon. [n. d.]. Amazon Rekognition: Automate your image recognition and video analysis with machine learning. https://aws.amazon.com/rekognition/

2. Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, and Matthias Hein. 2020. Square attack: a query-efficient black-box adversarial attack via random search. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIII. Springer, 484--501.

3. Anish Athalye, Nicholas Carlini, and David Wagner. 2018. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In International conference on machine learning. PMLR, 274--283.

4. Amin Azmoodeh, Ali Dehghantanha, and Kim-Kwang Raymond Choo. 2018. Robust malware detection for internet of (battlefield) things devices using deep eigenspace learning. IEEE transactions on sustainable computing, Vol. 4, 1 (2018), 88--95.

5. Sean Bell and Kavita Bala. 2015. Learning visual similarity for product design with convolutional neural networks. ACM transactions on graphics (TOG), Vol. 34, 4 (2015), 1--10.

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Towards Protecting On-Device Machine Learning with RISC-V based Multi-Enclave TEE;2024 33rd International Conference on Computer Communications and Networks (ICCCN);2024-07-29

2. L-AutoDA: Large Language Models for Automatically Evolving Decision-based Adversarial Attacks;Proceedings of the Genetic and Evolutionary Computation Conference Companion;2024-07-14

3. D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03