Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning
The prevalence and success of Deep Neural Network (DNN) applications in recent years have motivated research on DNN compression, such as pruning and quantization. These techniques accelerate model inference, reduce power consumption, and reduce the size and complexity of the hardware necessary to run DNNs, all with little to no loss in accuracy. However, since DNNs are vulnerable to adversarial inputs, it is important to consider the relationship between compression and adversarial robustness. In this work, we investigate the adversarial robustness of models produced by several irregular pruning schemes and by 8-bit quantization. Additionally, while conventional pruning removes the least important parameters in a DNN, we investigate the effect of an unconventional pruning method: removing the most important model parameters based on the gradient on adversarial inputs. We call this method Greedy Adversarial Pruning (GAP) and we find that this pruning method results in models that are resistant to transfer attacks from their uncompressed counterparts.
Code (1)
Tasks
Adversarial RobustnessQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks
Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as …
Hardening Deep Neural Networks via Adversarial Model Cascades
Deep neural networks (DNNs) are vulnerable to malicious inputs crafted by an adversary to produce erroneous outputs. Works on securing neural networks against adversarial examples achieve high empirical robustness on sim…
Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
In today's data-driven landscape, the delicate equilibrium between safeguarding user privacy and unleashing data potential stands as a paramount concern. Federated learning, which enables collaborative model training wit…
Adversarial RobustnessFederated LearningExploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks
We investigate to what extent alternative variants of Artificial Neural Networks (ANNs) are susceptible to adversarial attacks. We analyse the adversarial robustness of conventional, stochastic ANNs and Spiking Neural Ne…
Adversarial RobustnessExploring the Space of Black-box Attacks on Deep Neural Networks
Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models…