Rethinking Feature Uncertainty in Stochastic Neural Networks for Adversarial Robustness
It is well-known that deep neural networks (DNNs) have shown remarkable success in many fields. However, when adding an imperceptible magnitude perturbation on the model input, the model performance might get rapid decrease. To address this issue, a randomness technique has been proposed recently, named Stochastic Neural Networks (SNNs). Specifically, SNNs inject randomness into the model to defend against unseen attacks and improve the adversarial robustness. However, existed studies on SNNs mainly focus on injecting fixed or learnable noises to model weights/activations. In this paper, we find that the existed SNNs performances are largely bottlenecked by the feature representation ability. Surprisingly, simply maximizing the variance per dimension of the feature distribution leads to a considerable boost beyond all previous methods, which we named maximize feature distribution variance stochastic neural network (MFDV-SNN). Extensive experiments on well-known white- and black-box attacks show that MFDV-SNN achieves a significant improvement over existing methods, which indicates that it is a simple but effective method to improve model robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Rethinking Uncertainty in Deep Learning: Whether and How it Improves Robustness
Deep neural networks (DNNs) are known to be prone to adversarial attacks, for which many remedies are proposed. While adversarial training (AT) is regarded as the most robust defense, it suffers from poor performance bot…
Feature Statistics with Uncertainty Help Adversarial Robustness
Despite the remarkable success of deep neural networks (DNNs), the security threat of adversarial attacks poses a significant challenge to the reliability of DNNs. By introducing randomness into different parts of DNNs, …
Adversarial RobustnessDR-PETS: Learning-Based Control With Planning in Adversarial Environments
Ensuring robustness against epistemic, possibly adversarial, perturbations is essential for reliable real-world decision-making. While the Probabilistic Ensembles with Trajectory Sampling (PETS) algorithm inherently hand…
Decision MakingDefense Through Diverse Directions
In this work we develop a novel Bayesian neural network methodology to achieve strong adversarial robustness without the need for online adversarial training. Unlike previous efforts in this direction, we do not rely sol…
Adversarial RobustnessA unifying Bayesian framework for adversarial robustness
The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge. Traditional defenses, such as adversarial training, typically robustify models by minimizing a worst-cas…
Adversarial Robustness