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

Abstract

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.

References in corpus (17)

• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Detecting Adversarial Samples from Artifacts
• Robustness May Be at Odds with Accuracy
• Deep Variational Information Bottleneck
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• On Physical Adversarial Patches for Object Detection
• Dropout Inference in Bayesian Neural Networks with Alpha-divergences
• Adversarial camera stickers: A physical camera-based attack on deep learning systems
• Defensive Quantization: When Efficiency Meets Robustness
• Bypassing Feature Squeezing by Increasing Adversary Strength
• To be Robust or to be Fair: Towards Fairness in Adversarial Training
• Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts
• The Taboo Trap: Behavioural Detection of Adversarial Samples
• The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms

Cited by in corpus (1)

• High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm