# HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks

arXiv: https://arxiv.org/abs/2106.05825 · HTML: https://mlsanity.com/paper/2106.05825/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 66 references that are in the map.
- First posted on arXiv 9 Jun 2021.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality](https://mlsanity.com/paper/1801.02613/) (2018)
- [Stochastic Activation Pruning for Robust Adversarial Defense](https://mlsanity.com/paper/1803.01442/) (2018)
- [EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples](https://mlsanity.com/paper/1709.04114/) (2017)
- [SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks](https://mlsanity.com/paper/1708.04485/) (2017)
- [Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack](https://mlsanity.com/paper/1811.09310/) (2018)
- [Are adversarial examples inevitable?](https://mlsanity.com/paper/1809.02104/) (2018)
- [The Odds are Odd: A Statistical Test for Detecting Adversarial Examples](https://mlsanity.com/paper/1902.04818/) (2019)
- [How Important Is a Neuron?](https://mlsanity.com/paper/1805.12233/) (2018)
- [Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification](https://mlsanity.com/paper/1709.05583/) (2017)
- [Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reduction](https://mlsanity.com/paper/1705.08378/) (2017)
- [A New Defense Against Adversarial Images: Turning a Weakness into a Strength](https://mlsanity.com/paper/1910.07629/) (2019)

## Abstract (arXiv)

Deep Neural Networks (DNNs) are employed in an increasing number of applications, some of which are safety critical. Unfortunately, DNNs are known to be vulnerable to so-called adversarial attacks that manipulate inputs to cause incorrect results that can be beneficial to an attacker or damaging to the victim. Multiple defenses have been proposed to increase the robustness of DNNs. In general, these defenses have high overhead, some require attack-specific re-training of the model or careful tuning to adapt to different attacks. This paper presents HASI, a hardware-accelerated defense that uses a process we call stochastic inference to detect adversarial inputs. We show that by carefully injecting noise into the model at inference time, we can differentiate adversarial inputs from benign ones. HASI uses the output distribution characteristics of noisy inference compared to a non-noisy reference to detect adversarial inputs. We show an adversarial detection rate of 86% when applied to VGG16 and 93% when applied to ResNet50, which exceeds the detection rate of the state of the art approaches, with a much lower overhead. We demonstrate two software/hardware-accelerated co-designs, which reduces the performance impact of stochastic inference to 1.58X-2X relative to the unprotected baseline, compared to 15X-20X overhead for a software-only GPU implementation.