# QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks

arXiv: https://arxiv.org/abs/1811.01437 · HTML: https://mlsanity.com/paper/1811.01437/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2018.

## Built on by (most cited first, 21 of 21)

- [WaveGuard: Understanding and Mitigating Audio Adversarial Examples](https://mlsanity.com/paper/2103.03344/) (2021)
- [Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey](https://mlsanity.com/paper/2203.08737/) (2022)
- [CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization](https://mlsanity.com/paper/2411.12768/) (2024)
- [CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models](https://mlsanity.com/paper/2406.12257/) (2024)
- [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework](https://mlsanity.com/paper/2109.09829/) (2021)
- [Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference](https://mlsanity.com/paper/2603.13461/) (2026)
- [Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems](https://mlsanity.com/paper/2204.09514/) (2022)
- [Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning](https://mlsanity.com/paper/2410.11205/) (2024)
- [Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks](https://mlsanity.com/paper/2105.03251/) (2021)
- [RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression](https://mlsanity.com/paper/2203.10183/) (2022)
- [Is Approximation Universally Defensive Against Adversarial Attacks in Deep Neural Networks?](https://mlsanity.com/paper/2112.01555/) (2021)
- [Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses](https://mlsanity.com/paper/2210.13289/) (2022)
- [Can collaborative learning be private, robust and scalable?](https://mlsanity.com/paper/2205.02652/) (2022)
- [Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications](https://mlsanity.com/paper/2112.02819/) (2021)
- [Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models](https://mlsanity.com/paper/2303.02669/) (2023)
- [Security-Aware Approximate Spiking Neural Networks](https://mlsanity.com/paper/2301.05264/) (2023)
- [DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks for Image Analysis](https://mlsanity.com/paper/2410.19794/) (2024)
- [Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs](https://mlsanity.com/paper/2601.14340/) (2026)
- [Defense Against LLM Backdoors using Critical Neuron Isolation Pruning](https://mlsanity.com/paper/2607.19894/) (2026)
- [Backdoor Containment via Expert Quarantine and Shutdown in LLMs](https://mlsanity.com/paper/2610.00663/) (2026)
- [Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection](https://mlsanity.com/paper/2610.00685/) (2026)

## Abstract (arXiv)

Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quantization-based defense mechanisms, Constant Quantization (CQ) and Trainable Quantization (TQ), to increase the robustness of CNNs against adversarial examples. CQ quantizes input pixel intensities based on a "fixed" number of quantization levels, while in TQ, the quantization levels are "iteratively learned during the training phase", thereby providing a stronger defense mechanism. We apply the proposed techniques on undefended CNNs against different state-of-the-art adversarial attacks from the open-source textitCleverhans library. The experimental results demonstrate 50%-96% and 10%-50% increase in the classification accuracy of the perturbed images generated from the MNIST and the CIFAR-10 datasets, respectively, on commonly used CNN (Conv2D(64, 8x8) - Conv2D(128, 6x6) - Conv2D(128, 5x5) - Dense(10) - Softmax()) available in textitCleverhans library.