Log In Sign Up

Mitigating Gradient-based Adversarial Attacks via Denoising and Compression

by   Rehana Mahfuz, et al.

Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network, and the risk they introduce cannot be assessed through the network's original training performance. Denoising and dimensionality reduction are two distinct methods that have been independently investigated to combat such attacks. While denoising offers the ability to tailor the defense to the specific nature of the attack, dimensionality reduction offers the advantage of potentially removing previously unseen perturbations, along with reducing the training time of the network being defended. We propose strategies to combine the advantages of these two defense mechanisms. First, we propose the cascaded defense, which involves denoising followed by dimensionality reduction. To reduce the training time of the defense for a small trade-off in performance, we propose the hidden layer defense, which involves feeding the output of the encoder of a denoising autoencoder into the network. Further, we discuss how adaptive attacks against these defenses could become significantly weak when an alternative defense is used, or when no defense is used. In this light, we propose a new metric to evaluate a defense which measures the sensitivity of the adaptive attack to modifications in the defense. Finally, we present a guideline for building an ordered repertoire of defenses, a.k.a. a defense infrastructure, that adjusts to limited computational resources in presence of uncertainty about the attack strategy.


A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks

The reliance on deep learning algorithms has grown significantly in rece...

On the Limitations of Denoising Strategies as Adversarial Defenses

As adversarial attacks against machine learning models have raised incre...

Ensemble Noise Simulation to Handle Uncertainty about Gradient-based Adversarial Attacks

Gradient-based adversarial attacks on neural networks can be crafted in ...

Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach

Machine Learning models are vulnerable to adversarial attacks that rely ...

Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things

Nowadays, Deep Learning as a service can be deployed in Internet of Thin...

BUZz: BUffer Zones for defending adversarial examples in image classification

We propose a novel defense against all existing gradient based adversari...

Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks

Deep learning (DL) offers potential improvements throughout the CAD tool...