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

arXiv: https://arxiv.org/abs/2105.06512 · HTML: https://mlsanity.com/paper/2105.06512/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 28 references that are in the map.
- First posted on arXiv 13 May 2021.

## Builds on (most cited first, 26 of 26)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Detecting Adversarial Samples from Artifacts](https://mlsanity.com/paper/1703.00410/) (2017)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference](https://mlsanity.com/paper/1506.02158/) (2015)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [Defensive Quantization: When Efficiency Meets Robustness](https://mlsanity.com/paper/1904.08444/) (2019)
- [On Physical Adversarial Patches for Object Detection](https://mlsanity.com/paper/1906.11897/) (2019)
- [Adversarial camera stickers: A physical camera-based attack on deep learning systems](https://mlsanity.com/paper/1904.00759/) (2019)
- [Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks](https://mlsanity.com/paper/1707.02476/) (2017)
- [Dropout Inference in Bayesian Neural Networks with Alpha-divergences](https://mlsanity.com/paper/1703.02914/) (2017)
- [Ptolemy: Architecture Support for Robust Deep Learning](https://mlsanity.com/paper/2008.09954/) (2020)
- [Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts](https://mlsanity.com/paper/2009.02967/) (2020)
- [Bypassing Feature Squeezing by Increasing Adversary Strength](https://mlsanity.com/paper/1803.09868/) (2018)
- [The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms](https://mlsanity.com/paper/2102.05956/) (2021)
- [The Taboo Trap: Behavioural Detection of Adversarial Samples](https://mlsanity.com/paper/1811.07375/) (2018)

## Built on by (most cited first, 5 of 5)

- [When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA](https://mlsanity.com/paper/2308.06849/) (2023)
- [Enhancing the Security & Privacy of Wearable Brain-Computer Interfaces](https://mlsanity.com/paper/2201.07711/) (2022)
- [High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm](https://mlsanity.com/paper/2107.10746/) (2021)
- [ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs](https://mlsanity.com/paper/2410.24214/) (2024)
- [On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models](https://mlsanity.com/paper/2608.10530/) (2026)

## Abstract (arXiv)

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.