paper-with-me

홈 › Papers

Exploring Biologically Inspired Mechanisms of Adversarial Robustness

2024-02-05 · Konstantin Holzhausen, Mia Merlid, Håkon Olav Torvik, Anders Malthe-Sørenssen, Mikkel Elle Lepperød

Backpropagation-optimized artificial neural networks, while precise, lack robustness, leading to unforeseen behaviors that affect their safety. Biological neural systems do solve some of these issues already. Unlike artificial models, biological neurons adjust connectivity based on neighboring cell activity. Understanding the biological mechanisms of robustness can pave the way towards building trust worthy and safe systems. Robustness in neural representations is hypothesized to correlate with the smoothness of the encoding manifold. Recent work suggests power law covariance spectra, which were observed studying the primary visual cortex of mice, to be indicative of a balanced trade-off between accuracy and robustness in representations. Here, we show that unsupervised local learning models with winner takes all dynamics learn such power law representations, providing upcoming studies a mechanistic model with that characteristic. Our research aims to understand the interplay between geometry, spectral properties, robustness, and expressivity in neural representations. Hence, we study the link between representation smoothness and spectrum by using weight, Jacobian and spectral regularization while assessing performance and adversarial robustness. Our work serves as a foundation for future research into the mechanisms underlying power law spectra and optimally smooth encodings in both biological and artificial systems. The insights gained may elucidate the mechanisms that realize robust neural networks in mammalian brains and inform the development of more stable and reliable artificial systems.

📄 PDF Abstract BibTeX arXiv:2405.00679

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Biologically Inspired Mechanisms for Adversarial Robustness

2020-06-29 · NeurIPS 2020 12 · Manish V. Reddy, Andrzej Banburski, Nishka Pant, Tomaso Poggio

A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventral stream seems to be robust to small pe…

Adversarial Robustness

SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense

2025-10-09 · Jiayang Liu, Daniel Tso, Yiming Bu, Qinru Qiu arxiv

Adversarial attacks significantly challenge the safe deployment of deep learning models, particularly in real-world applications. Traditional defenses often rely on computationally intensive optimization (e.g., adversari…

Reinforcement LearningAdversarial DefenseData Augmentation

Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey

2023-07-30 · Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato

Recently emerged technologies based on Deep Learning (DL) achieved outstanding results on a variety of tasks in the field of Artificial Intelligence (AI). However, these encounter several challenges related to robustness…

Deep Learning

Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception

2021-11-12 · NeurIPS 2021 12 · Joel Dapello, Jenelle Feather, Hang Le, Tiago Marques 외

Adversarial examples are often cited by neuroscientists and machine learning researchers as an example of how computational models diverge from biological sensory systems. Recent work has proposed adding biologically-ins…

Adversarial Robustness

Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networks

2020-05-01 · ICLR 2020 1 · Timothy Tadros, Giri Krishnan, Ramyaa Ramyaa, Maxim Bazhenov

Current artificial neural networks (ANNs) can perform and excel at a variety of tasks ranging from image classification to spam detection through training on large datasets of labeled data. While the trained network may …

Adversarial RobustnessGeneral Classificationimage-classificationImage Classification+1