# DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

arXiv: https://arxiv.org/abs/1702.06763 · HTML: https://mlsanity.com/paper/1702.06763/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2017.

## Built on by (most cited first, 22 of 22)

- [Sparsity Winning Twice: Better Robust Generalization from More Efficient Training](https://mlsanity.com/paper/2202.09844/) (2022)
- [Generative Dynamic Patch Attack](https://mlsanity.com/paper/2111.04266/) (2021)
- [Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2307.07187/) (2023)
- [Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking](https://mlsanity.com/paper/2407.13646/) (2024)
- [A Unified Game-Theoretic Interpretation of Adversarial Robustness](https://mlsanity.com/paper/2111.03536/) (2021)
- [Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free](https://mlsanity.com/paper/2205.11819/) (2022)
- [Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness](https://mlsanity.com/paper/2206.07839/) (2022)
- [Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective](https://mlsanity.com/paper/2101.03042/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review](https://mlsanity.com/paper/2102.02729/) (2021)
- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice](https://mlsanity.com/paper/2102.01979/) (2021)
- [Hierarchical Testing with Rabbit Optimization for Industrial Cyber-Physical Systems](https://mlsanity.com/paper/2507.04100/) (2025)
- [DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning](https://mlsanity.com/paper/2101.03218/) (2021)
- [A Random-patch based Defense Strategy Against Physical Attacks for Face Recognition Systems](https://mlsanity.com/paper/2304.07822/) (2023)
- [Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN](https://mlsanity.com/paper/2103.04513/) (2021)
- [A Unified Game-Theoretic Interpretation of Adversarial Robustness](https://mlsanity.com/paper/2103.07364/) (2021)
- [Benign Adversarial Attack: Tricking Models for Goodness](https://mlsanity.com/paper/2107.11986/) (2021)
- [Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning](https://mlsanity.com/paper/2206.07406/) (2022)
- [RobustPdM: Designing Robust Predictive Maintenance against Adversarial Attacks](https://mlsanity.com/paper/2301.10822/) (2023)
- [Improving Robustness of Deep Convolutional Neural Networks via Multiresolution Learning](https://mlsanity.com/paper/2309.13752/) (2023)
- [Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Review](https://mlsanity.com/paper/2506.15506/) (2025)

## Abstract (arXiv)

Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attacks can severely undermine DNN systems, particularly in security-sensitive settings. It was observed that an adversary could easily generate adversarial samples by making a small perturbation on irrelevant feature dimensions that are unnecessary for the current classification task. To overcome this problem, we introduce a defensive mechanism called DeepCloak. By identifying and removing unnecessary features in a DNN model, DeepCloak limits the capacity an attacker can use generating adversarial samples and therefore increase the robustness against such inputs. Comparing with other defensive approaches, DeepCloak is easy to implement and computationally efficient. Experimental results show that DeepCloak can increase the performance of state-of-the-art DNN models against adversarial samples.