ILFO: Adversarial Attack on Adaptive Neural Networks
By Mirazul Haque, Anki Chauhan, Cong Liu, Wei Yang. 2020
41 citations recorded by the source corpus.
With the increasing number of layers and parameters in neural networks, the energy consumption of neural networks has become a great concern to society, especially to users of handheld or embedded devices. In this paper, we investigate the robustness of neural networks against energy-oriented attacks. Specifically, we propose ILFO (Intermediate Output-Based Loss Function Optimization) attack against a common type of energy-saving neural networks, Adaptive Neural Networks (AdNN). AdNNs save energy consumption by dynamically deactivating part of its model based on the need of the inputs. ILFO leverages intermediate output as a proxy to infer the relation between input and its corresponding energy consumption. ILFO has shown an increase up to 100 % of the FLOPs (floating-point operations per second) reduced by AdNNs with minimum noise added to input images. To our knowledge, this is the first attempt to attack the energy consumption of an AdNN.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
In Electrical and Electronic Engineering
In Safety, Robustness & Interpretability
Citations in the corpus
- Dynamic Neural Networks: A Survey (2021, background): “For dynamic networks, it is possible to launch attacks on efficiency [280], [281].”
- A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference (2020, background): “Haque et al. (2020) presented attacks specifically designed for reducing the energy-efficiency of AdNNs by using adversarial input perturbations.”