# Divide, Denoise, and Defend against Adversarial Attacks

arXiv: https://arxiv.org/abs/1802.06806 · HTML: https://mlsanity.com/paper/1802.06806/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2018.

## Built on by (most cited first, 12 of 12)

- [LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses](https://mlsanity.com/paper/2406.04755/) (2024)
- [Defenses in Adversarial Machine Learning: A Survey](https://mlsanity.com/paper/2312.08890/) (2023)
- [Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness](https://mlsanity.com/paper/2309.16096/) (2023)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Perturbation Inactivation Based Adversarial Defense for Face Recognition](https://mlsanity.com/paper/2207.06035/) (2022)
- [Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks](https://mlsanity.com/paper/2112.14232/) (2021)
- [Reverse Engineering ℓp attacks: A block-sparse optimization approach with recovery guarantees](https://mlsanity.com/paper/2203.04886/) (2022)
- [Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustness](https://mlsanity.com/paper/2106.02867/) (2021)
- [Artificial Immune System of Secure Face Recognition Against Adversarial Attacks](https://mlsanity.com/paper/2406.18144/) (2024)
- [Group-based Robustness: A General Framework for Customized Robustness in the Real World](https://mlsanity.com/paper/2306.16614/) (2023)
- [A Practical Adversarial Attack on Contingency Detection of Smart Energy Systems](https://mlsanity.com/paper/2109.06358/) (2021)
- [Enhancing robustness of data-driven SHM models: adversarial training with circle loss](https://mlsanity.com/paper/2406.14232/) (2024)

## Abstract (arXiv)

Deep neural networks, although shown to be a successful class of machine learning algorithms, are known to be extremely unstable to adversarial perturbations. Improving the robustness of neural networks against these attacks is important, especially for security-critical applications. To defend against such attacks, we propose dividing the input image into multiple patches, denoising each patch independently, and reconstructing the image, without losing significant image content. We call our method D3. This proposed defense mechanism is non-differentiable which makes it non-trivial for an adversary to apply gradient-based attacks. Moreover, we do not fine-tune the network with adversarial examples, making it more robust against unknown attacks. We present an analysis of the tradeoff between accuracy and robustness against adversarial attacks. We evaluate our method under black-box, grey-box, and white-box settings. On the ImageNet dataset, our method outperforms the state-of-the-art by 19.7% under grey-box setting, and performs comparably under black-box setting. For the white-box setting, the proposed method achieves 34.4% accuracy compared to the 0% reported in the recent works.