Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs

by   Lorena Qendro, et al.

Quantized neural networks (NN) are the common standard to efficiently deploy deep learning models on tiny hardware platforms. However, we notice that quantized NNs are as vulnerable to adversarial attacks as the full-precision models. With the proliferation of neural networks on small devices that we carry or surround us, there is a need for efficient models without sacrificing trust in the prediction in presence of malign perturbations. Current mitigation approaches often need adversarial training or are bypassed when the strength of adversarial examples is increased. In this work, we investigate how a probabilistic framework would assist in overcoming the aforementioned limitations for quantized deep learning models. We explore Stochastic-Shield: a flexible defense mechanism that leverages input filtering and a probabilistic deep learning approach materialized via Monte Carlo Dropout. We show that it is possible to jointly achieve efficiency and robustness by accurately enabling each module without the burden of re-retraining or ad hoc fine-tuning.



There are no comments yet.


page 5


Defensive Quantization: When Efficiency Meets Robustness

Neural network quantization is becoming an industry standard to efficien...

A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustness

Neural networks are getting better accuracy with higher energy and compu...

Stochastic Activation Pruning for Robust Adversarial Defense

Neural networks are known to be vulnerable to adversarial examples. Care...

Fast and Scalable Adversarial Training of Kernel SVM via Doubly Stochastic Gradients

Adversarial attacks by generating examples which are almost indistinguis...

Improving Adversarial Robustness in Weight-quantized Neural Networks

Neural networks are getting deeper and more computation-intensive nowada...

MTJ-Based Hardware Synapse Design for Quantized Deep Neural Networks

Quantized neural networks (QNNs) are being actively researched as a solu...

Deep Detector Health Management under Adversarial Campaigns

Machine learning models are vulnerable to adversarial inputs that induce...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.