# DDDM: a Brain-Inspired Framework for Robust Classification

arXiv: https://arxiv.org/abs/2205.10117 · HTML: https://mlsanity.com/paper/2205.10117/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 1 May 2022.

## Builds on (most cited first, 16 of 16)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [Stochastic Activation Pruning for Robust Adversarial Defense](https://mlsanity.com/paper/1803.01442/) (2018)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- [Adversarial Examples that Fool both Computer Vision and Time-Limited Humans](https://mlsanity.com/paper/1802.08195/) (2018)
- [Fast Differentiable Clipping-Aware Normalization and Rescaling](https://mlsanity.com/paper/2007.07677/) (2020)

## Built on by (most cited first, 3 of 3)

- [Visual Adversarial Attacks and Defenses in the Physical World: A Survey](https://mlsanity.com/paper/2211.01671/) (2022)
- [Adversarial Examples in the Physical World: A Survey](https://mlsanity.com/paper/2311.01473/) (2023)
- [Exploring The Neural Burden In Pruned Models: An Insight Inspired By Neuroscience](https://mlsanity.com/paper/2407.16716/) (2024)

## Abstract (arXiv)

Despite their outstanding performance in a broad spectrum of real-world tasks, deep artificial neural networks are sensitive to input noises, particularly adversarial perturbations. On the contrary, human and animal brains are much less vulnerable. In contrast to the one-shot inference performed by most deep neural networks, the brain often solves decision-making with an evidence accumulation mechanism that may trade time for accuracy when facing noisy inputs. The mechanism is well described by the Drift-Diffusion Model (DDM). In the DDM, decision-making is modeled as a process in which noisy evidence is accumulated toward a threshold. Drawing inspiration from the DDM, we propose the Dropout-based Drift-Diffusion Model (DDDM) that combines test-phase dropout and the DDM for improving the robustness for arbitrary neural networks. The dropouts create temporally uncorrelated noises in the network that counter perturbations, while the evidence accumulation mechanism guarantees a reasonable decision accuracy. Neural networks enhanced with the DDDM tested in image, speech, and text classification tasks all significantly outperform their native counterparts, demonstrating the DDDM as a task-agnostic defense against adversarial attacks.