# Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes

arXiv: https://arxiv.org/abs/2004.00306 · HTML: https://mlsanity.com/paper/2004.00306/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 15 of 15)

- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [Adversarial Visual Robustness by Causal Intervention](https://mlsanity.com/paper/2106.09534/) (2021)
- [Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser](https://mlsanity.com/paper/2304.06430/) (2023)
- [Impact of Spatial Frequency Based Constraints on Adversarial Robustness](https://mlsanity.com/paper/2104.12679/) (2021)
- [ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2107.07677/) (2021)
- [Certified Adversarial Robustness Within Multiple Perturbation Bounds](https://mlsanity.com/paper/2304.10446/) (2023)
- [Adversarial Parameter Defense by Multi-Step Risk Minimization](https://mlsanity.com/paper/2109.02889/) (2021)
- [Rethinking Feature Uncertainty in Stochastic Neural Networks for Adversarial Robustness](https://mlsanity.com/paper/2201.00148/) (2022)
- [Data-free Defense of Black Box Models Against Adversarial Attacks](https://mlsanity.com/paper/2211.01579/) (2022)
- [SAFE: Secure and Accurate Federated Learning for Privacy-Preserving Brain-Computer Interfaces](https://mlsanity.com/paper/2601.05789/) (2026)
- [RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks](https://mlsanity.com/paper/2603.15413/) (2026)
- [Are We There Yet? Unraveling the State-of-the-Art Graph Network Intrusion Detection Systems](https://mlsanity.com/paper/2503.20281/) (2025)
- [Generating Transferrable Adversarial Examples via Local Mixing and Logits Optimization for Remote Sensing Object Recognition](https://mlsanity.com/paper/2509.07495/) (2025)
- [Robust Few-shot Learning Without Using any Adversarial Samples](https://mlsanity.com/paper/2211.01598/) (2022)

## Abstract (arXiv)

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously crafted perturbations that are nearly imperceptible to the human eye. In this work, we attempt to address this problem by training networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction. We demonstrate that, by imposing consistency on the representations learned across differently quantized images, the adversarial robustness of networks improves significantly when compared to a normally trained model. Present state-of-the-art defenses against adversarial attacks require the networks to be explicitly trained using adversarial samples that are computationally expensive to generate. While such methods that use adversarial training continue to achieve the best results, this work paves the way towards achieving robustness without having to explicitly train on adversarial samples. The proposed approach is therefore faster, and also closer to the natural learning process in humans.