# Efficient Defenses Against Adversarial Attacks

arXiv: https://arxiv.org/abs/1707.06728 · HTML: https://mlsanity.com/paper/1707.06728/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2017.

## Built on by (most cited first, 30 of 53)

- [SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)](https://mlsanity.com/paper/2108.04974/) (2021)
- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [Relating Adversarially Robust Generalization to Flat Minima](https://mlsanity.com/paper/2104.04448/) (2021)
- [Subspace Adversarial Training](https://mlsanity.com/paper/2111.12229/) (2021)
- [Biometrics: Trust, but Verify](https://mlsanity.com/paper/2105.06625/) (2021)
- [A Review of Adversarial Attack and Defense for Classification Methods](https://mlsanity.com/paper/2111.09961/) (2021)
- [Parameterizing Activation Functions for Adversarial Robustness](https://mlsanity.com/paper/2110.05626/) (2021)
- [MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification](https://mlsanity.com/paper/2406.05927/) (2024)
- [Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking](https://mlsanity.com/paper/2407.13646/) (2024)
- [On the Inherent Regularization Effects of Noise Injection During Training](https://mlsanity.com/paper/2102.07379/) (2021)
- [Targeted Attack Improves Protection against Unauthorized Diffusion Customization](https://mlsanity.com/paper/2310.04687/) (2023)
- [A PAC-Bayes Analysis of Adversarial Robustness](https://mlsanity.com/paper/2102.11069/) (2021)
- [A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness](https://mlsanity.com/paper/2212.09006/) (2022)
- [FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis](https://mlsanity.com/paper/2308.05362/) (2023)
- [MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation](https://mlsanity.com/paper/2209.04471/) (2022)
- [Towards Robust Model Watermark via Reducing Parametric Vulnerability](https://mlsanity.com/paper/2309.04777/) (2023)
- [Morphence: Moving Target Defense Against Adversarial Examples](https://mlsanity.com/paper/2108.13952/) (2021)
- [Defending Against Backdoor Attack on Graph Nerual Network by Explainability](https://mlsanity.com/paper/2209.02902/) (2022)
- [Learning Provably Robust Estimators for Inverse Problems via Jittering](https://mlsanity.com/paper/2307.12822/) (2023)
- [Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System](https://mlsanity.com/paper/2310.03334/) (2023)
- [Certification of embedded systems based on Machine Learning: A survey](https://mlsanity.com/paper/2106.07221/) (2021)
- [Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs](https://mlsanity.com/paper/2208.12428/) (2022)
- [Explaining Adversarial Vulnerability with a Data Sparsity Hypothesis](https://mlsanity.com/paper/2103.00778/) (2021)
- [Trustworthy AI and Robotics and the Implications for the AEC Industry: A Systematic Literature Review and Future Potentials](https://mlsanity.com/paper/2109.13373/) (2021)
- [One-stage Modality Distillation for Incomplete Multimodal Learning](https://mlsanity.com/paper/2309.08204/) (2023)
- [Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoising](https://mlsanity.com/paper/2107.05780/) (2021)
- [Adversarial Machine Learning Threat Analysis and Remediation in Open Radio Access Network (O-RAN)](https://mlsanity.com/paper/2201.06093/) (2022)
- [Hessian-Free Second-Order Adversarial Examples for Adversarial Learning](https://mlsanity.com/paper/2207.01396/) (2022)
- [Countering Adversarial Examples: Combining Input Transformation and Noisy Training](https://mlsanity.com/paper/2106.13394/) (2021)
- [Memory Defense: More Robust Classification via a Memory-Masking Autoencoder](https://mlsanity.com/paper/2202.02595/) (2022)

## Abstract (arXiv)

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinforce the structure of a DNN, making its prediction more stable and less likely to be fooled by adversarial samples. We conduct an extensive experimental study proving the efficiency of our method against multiple attacks, comparing it to numerous defenses, both in white-box and black-box setups. Additionally, the implementation of our method brings almost no overhead to the training procedure, while maintaining the prediction performance of the original model on clean samples.