Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks
Despite its great success, deep learning severely suffers from robustness; that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones. Inspired by recent advances in brain science, we propose the Denoised Internal Models (DIM), a novel generative autoencoder-based model to tackle this challenge. Simulating the pipeline in the human brain for visual signal processing, DIM adopts a two-stage approach. In the first stage, DIM uses a denoiser to reduce the noise and the dimensions of inputs, reflecting the information pre-processing in the thalamus. Inspired from the sparse coding of memory-related traces in the primary visual cortex, the second stage produces a set of internal models, one for each category. We evaluate DIM over 42 adversarial attacks, showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
Artificial neural networks (ANNs) continue to face challenges in continual learning, particularly due to catastrophic forgetting, the loss of previously learned knowledge when acquiring new tasks. Inspired by memory cons…
Continual LearningCombatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach
Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against …
BIG-bench Machine LearningDenoisingDimensionality ReductionMultiMAE for Brain MRIs: Robustness to Missing Inputs Using Multi-Modal Masked Autoencoder
Missing input sequences are common in medical imaging data, posing a challenge for deep learning models reliant on complete input data. In this work, inspired by MultiMAE [2], we develop a masked autoencoder (MAE) paradi…
Multi-Task LearningBrain-Inspired Architectures for Efficient and Meaningful Learning from Temporally Smooth Data
How can learning systems exploit the temporal smoothness of real-world training data? We tested the learning of neural networks equipped with two architectural features inspired by the temporal properties of neural circu…
Robustifying Diffusion-Denoised Smoothing Against Covariate Shift
Randomized smoothing is a well-established method for achieving certified robustness against l2-adversarial perturbations. By incorporating a denoiser before the base classifier, pretrained classifiers can be seamlessly …