paper-with-me

홈 › Papers

One Neuron to Fool Them All

2020-03-20 · Anshuman Suri, David Evans

Despite vast research in adversarial examples, the root causes of model susceptibility are not well understood. Instead of looking at attack-specific robustness, we propose a notion that evaluates the sensitivity of individual neurons in terms of how robust the model's output is to direct perturbations of that neuron's output. Analyzing models from this perspective reveals distinctive characteristics of standard as well as adversarially-trained robust models, and leads to several curious results. In our experiments on CIFAR-10 and ImageNet, we find that attacks using a loss function that targets just a single sensitive neuron find adversarial examples nearly as effectively as ones that target the full model. We analyze the properties of these sensitive neurons to propose a regularization term that can help a model achieve robustness to a variety of different perturbation constraints while maintaining accuracy on natural data distributions. Code for all our experiments is available at https://github.com/iamgroot42/sauron .

📄 PDF Abstract BibTeX arXiv:2003.09372

Code (1)

iamgroot42/sauron 공식 구현 pytorch

Tasks

All

Similar Papers 제목 키워드 기반

NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability

2025-08-23 · Krishna Kanth Nakka, Alexandre Alahi arxiv

The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work…

FooBaR: Fault Fooling Backdoor Attack on Neural Network Training

2021-09-23 · Jakub Breier, Xiaolu Hou, Martín Ochoa, Jesus Solano

Neural network implementations are known to be vulnerable to physical attack vectors such as fault injection attacks. As of now, these attacks were only utilized during the inference phase with the intention to cause a m…

Backdoor Attackimage-classificationImage Classification

Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks

2023-03-06 · Yiran Li, Junpeng Wang, Takanori Fujiwara, Kwan-Liu Ma

Adversarial attacks on a convolutional neural network (CNN) -- injecting human-imperceptible perturbations into an input image -- could fool a high-performance CNN into making incorrect predictions. The success of advers…

Autonomous DrivingMedical DiagnosisVisual Reasoning

Finite Gaussian Neurons: Defending against adversarial attacks by making neural networks say "I don't know"

2023-06-13 · Felix Grezes

Since 2014, artificial neural networks have been known to be vulnerable to adversarial attacks, which can fool the network into producing wrong or nonsensical outputs by making humanly imperceptible alterations to inputs…

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence

2021-12-24 · Ruoxi Chen, Haibo Jin, Haibin Zheng, Jinyin Chen 외

The vulnerabilities of deep learning models towards adversarial attacks have attracted increasing attention, especially when models are deployed in security-critical domains. Numerous defense methods, including reactive …