all InfoSec news
Attacking the Performance of Machine Learning Systems
Security Boulevard securityboulevard.com
Interesting research: “Sponge Examples: Energy-Latency Attacks on Neural Networks“:
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 or decision latency are …
academic papers analytics & intelligence cyberattack machine machine learning performance systems threats & breaches