And/or trade-off in artificial neurons: impact on adversarial robustness
Despite the success of neural networks, the issue of classification robustness remains, particularly highlighted by adversarial examples. In this paper, we address this challenge by focusing on the continuum of functions implemented in artificial neurons, ranging from pure AND gates to pure OR gates. Our hypothesis is that the presence of a sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. These measures involve rescaling inputs to the [-1,1] interval and reducing the number of points in the steepest section of the sigmoidal activation function. A crucial component of our method is the comparison between a neuron's output distribution when fed with the actual dataset and a randomised version called the "scrambled dataset." Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessBIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Impact of Adversarial Training on Robustness and Generalizability of Language Models
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained model…
Data AugmentationExploring Biologically Inspired Mechanisms of Adversarial Robustness
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 arti…
Adversarial RobustnessFault Tolerance of Neural Networks in Adversarial Settings
Artificial Intelligence systems require a through assessment of different pillars of trust, namely, fairness, interpretability, data and model privacy, reliability (safety) and robustness against against adversarial atta…
Adversarial RobustnessFairnessEnhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and decision-making. Despite their transformin…
Adversarial RobustnessDecision MakingArchitecture Selection via the Trade-off Between Accuracy and Robustness
We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning. We propose a method and define quantities to characterize the trade-off between accuracy and robustn…
Adversarial Attack