Abstract | ||
---|---|---|
The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While such devices enable us to train large-scale neural networks in datacenters and deploy them on edge devices, their designers' focus so far is on average-case performance. In this work, we introduce a novel threat vector against neural networks whose energy consumption ... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/EuroSP51992.2021.00024 | 2021 IEEE European Symposium on Security and Privacy (EuroS&P) |
Keywords | DocType | ISBN |
availability attacks,adversarial machine learning,adversarial examples,sponge examples,latency attacks,denial of service | Conference | 978-1-6654-1491-3 |
Citations | PageRank | References |
1 | 0.36 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shumailov Ilia | 1 | 1 | 0.36 |
Yiren Zhao | 2 | 11 | 5.27 |
Bates, Daniel | 3 | 1 | 1.03 |
Nicolas Papernot | 4 | 1932 | 87.62 |
Robert Mullins | 5 | 277 | 29.18 |
Ross J. Anderson | 6 | 5349 | 971.91 |