首页/论文/1808.07945

arXiv 1808.079452018-08-23cs.LGstat.ML

Maximal Jacobian-based Saliency Map Attack

Element AI

Rey Wiyatno, Anqi Xu

备注：: Extended version of extended abstract for MAIS 2018

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The Jacobian-based Saliency Map Attack is a family of adversarial attack methods for fooling classification models, such as deep neural networks for image classification tasks. By saturating a few pixels in a given image to their maximum or minimum values, JSMA can cause the model to misclassify the resulting adversarial image as a specified erroneous target class. We propose two variants of JSMA, one which removes the requirement to specify a target class, and another that additionally does not need to specify whether to only increase or decrease pixel intensities. Our experiments highlight the competitive speeds and qualities of these variants when applied to datasets of hand-written digits and natural scenes.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

JEPA世界模型的雅可比质心行为监测

Behavioral Monitoring of JEPA World Models with Jacobian Centroids

Rice University（莱斯大学）；Brown University（布朗大学）

本文提出用雅可比质心监测JEPA世界模型的行为对齐，发现编码器与预测器的结构分离可预测规划失败，并优于基线作为分布偏移检测器。

2026-09-29cs.LG

Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense

Anhui University（安徽大学）；The University of Western Australia（西澳大学）；Swansea University（斯旺西大学）

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples that are crafted with imperceptible perturbations, i.e., a small change in an input image can induce a mis-classification, and thus threatens the reliability of deep learning based deployment systems. Adversarial training (AT) is often adopted to improve robustness through training a mixture of corrupted and clean data. However, most of AT based methods are ineffective in dealing with transferred adversarial examples which are generated to fool a wide spectrum of defense models, and thus cannot satisfy the generaliz…

2022-11-14cs.AIcs.CRcs.LG

Probabilistic Jacobian-based Saliency Maps Attacks

CentraleSupélec（中央理工-高等电力学院）；IRT SystemX（SystemX技术研究院）

Neural network classifiers (NNCs) are known to be vulnerable to malicious adversarial perturbations of inputs including those modifying a small fraction of the input features named sparse or $L_0$ attacks. Effective and fast $L_0$ attacks, such as the widely used Jacobian-based Saliency Map Attack (JSMA) are practical to fool NNCs but also to improve their robustness. In this paper, we show that penalising saliency maps of JSMA by the output probabilities and the input features of the NNC allows to obtain more powerful attack algorithms that better take into account each input's characteristic…

2020-12-10cs.CRcs.CVcs.LG

Building Robust Deep Neural Networks for Road Sign Detection

Georgia Institute of Technology（佐治亚理工学院）；Twentieth Century Fox（二十世纪福克斯公司）；Starfleet Academy（星际舰队学院）；Tyrell Inc.（泰瑞尔公司）

Deep Neural Networks are built to generalize outside of training set in mind by using techniques such as regularization, early stopping and dropout. But considerations to make them more resilient to adversarial examples are rarely taken. As deep neural networks become more prevalent in mission-critical and real-time systems, miscreants start to attack them by intentionally making deep neural networks to misclassify an object of one type to be seen as another type. This can be catastrophic in some scenarios where the classification of a deep neural network can lead to a fatal decision by a mach…

2017-12-26cs.AIcs.LGstat.ML

Toward Robust Image Classification

Taibah University（泰巴大学）；University of Colorado at Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）

Neural networks are frequently used for image classification, but can be vulnerable to misclassification caused by adversarial images. Attempts to make neural network image classification more robust have included variations on preprocessing (cropping, applying noise, blurring), adversarial training, and dropout randomization. In this paper, we implemented a model for adversarial detection based on a combination of two of these techniques: dropout randomization with preprocessing applied to images within a given Bayesian uncertainty. We evaluated our model on the MNIST dataset, using adversari…

2019-09-19cs.CVcs.LGeess.IV

Art of singular vectors and universal adversarial perturbations

Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）

Vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has been attracting a lot of attention in recent studies. It has been shown that for many state of the art DNNs performing image classification there exist universal adversarial perturbations --- image-agnostic perturbations mere addition of which to natural images with high probability leads to their misclassification. In this work we propose a new algorithm for constructing such universal perturbations. Our approach is based on computing the so-called $(p, q)$-singular vectors of the Jacobian matrices of hidden layers of a n…

2017-11-20cs.AIcs.CVcs.LG

更多相关论文收起更多论文

Adversarial Attacks on Machine Learning Cybersecurity Defences in Industrial Control Systems

Cardiff University（卡迪夫大学）；Airbus（空中客车公司）

The proliferation and application of machine learning based Intrusion Detection Systems (IDS) have allowed for more flexibility and efficiency in the automated detection of cyber attacks in Industrial Control Systems (ICS). However, the introduction of such IDSs has also created an additional attack vector; the learning models may also be subject to cyber attacks, otherwise referred to as Adversarial Machine Learning (AML). Such attacks may have severe consequences in ICS systems, as adversaries could potentially bypass the IDS. This could lead to delayed attack detection which may result in i…

2020-04-10cs.CRcs.LGeess.SP

Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models

Stanford University（斯坦福大学）；SRI International（斯坦福国际研究院）

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically rely on saliency maps to quantify the voxel-wise or feature-level importance for classification through partial derivatives. Despite providing some level of localization, these maps are not human-understandable from the neuroscience perspective as they do not inform the specific meaning of the alteration linked to the brain disorder. Inspired by the image-t…

2021-06-26cs.CVcs.LGeess.IV

白盒对抗攻击对卷积神经网络的影响

Impact of White-Box Adversarial Attacks on Convolutional Neural Networks

Colorado State University（科罗拉多州立大学）

本文系统研究了多种白盒对抗攻击对CNN性能的影响，通过多个数据集和超参数实验揭示了CNN的脆弱性，并强调了开发鲁棒防御机制的紧迫性。

2024-10-02cs.CRcs.LGcs.NE

一种基于深度学习的新型模型以防御网络入侵检测系统免受对抗性攻击

A Novel Deep Learning based Model to Defend Network Intrusion Detection System against Adversarial Attacks

Bharati Vidyapeeth's Institute of Computer Applications and Management（巴拉蒂·维德亚佩特计算机应用与管理学院）；Aligarh Muslim University（阿里格尔穆斯林大学）

本研究针对基于深度学习的网络入侵检测系统（NIDS）易受对抗性攻击的问题，实现了FGSM、JSMA、PGD和C&W四种对抗攻击方法，并采用对抗训练作为防御手段，利用CICIDS-2017数据集在攻击前后及防御后三个阶段评估了模型性能。

2023-07-31cs.AIcs.CRcs.LG

Demystifying the Transferability of Adversarial Attacks in Computer Networks

Sabanci University（萨班哲大学）；University of Padua（帕多瓦大学）；Moulay Ismail University of Meknes（梅克内斯穆莱·伊斯梅尔大学）；Florida International University（佛罗里达国际大学）

Convolutional Neural Networks (CNNs) models are one of the most frequently used deep learning networks, and extensively used in both academia and industry. Recent studies demonstrated that adversarial attacks against such models can maintain their effectiveness even when used on models other than the one targeted by the attacker. This major property is known as transferability, and makes CNNs ill-suited for security applications. In this paper, we provide the first comprehensive study which assesses the robustness of CNN-based models for computer networks against adversarial transferability. F…

2022-03-31cs.AIcs.CRcs.CV

基于实时深度学习的网络入侵检测系统中结合启发式防御方法的无目标白盒对抗攻击研究

Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System

Aligarh Muslim University（阿里格尔穆斯林大学）

本研究针对基于深度学习的实时网络入侵检测系统的对抗漏洞问题，实现了四种白盒对抗攻击并验证其效果，同时提出三种启发式防御策略提升系统鲁棒性，为网络安全领域的对抗机器学习研究提供参考。

2023-10-07cs.LG

梳理计算机网络中对抗攻击迁移性的校正问题

Unscrambling the Rectification of Adversarial Attacks Transferability across Computer Networks

University of Leeds（利兹大学）；Bahcesehir University (BAU)（巴切谢希尔大学）；Cyber Science Lab（网络科学实验室）；University of Guelph（圭尔夫大学）

该研究针对CNN在网络安全等领域的对抗攻击脆弱性，提出评估攻击强度变化下对抗样本迁移性的方法，验证了多种攻击在计算机网络数据集上的迁移性提升，凸显了研发新型防御机制的必要性。

2023-10-26cs.AIcs.CRcs.LG

Thwarting Adversarial Examples: An $L_0$-RobustSparse Fourier Transform

Harvard University（哈佛大学）；MIT（麻省理工学院）

We give a new algorithm for approximating the Discrete Fourier transform of an approximately sparse signal that has been corrupted by worst-case $L_0$ noise, namely a bounded number of coordinates of the signal have been corrupted arbitrarily. Our techniques generalize to a wide range of linear transformations that are used in data analysis such as the Discrete Cosine and Sine transforms, the Hadamard transform, and their high-dimensional analogs. We use our algorithm to successfully defend against well known $L_0$ adversaries in the setting of image classification. We give experimental result…

2018-12-12cs.CRcs.DScs.LG

对抗样本生成用于工业控制系统中的异常检测

Adversarial Sample Generation for Anomaly Detection in Industrial Control Systems

DHA Suffa University（DHA Suffa大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Newcastle University（纽卡斯尔大学）

本文提出利用JSMA生成对抗样本以提升工业控制系统异常检测能力，通过在安全水处理测试平台评估，模型在未见过的真实攻击数据上达到95%的检测准确率。

2025-05-06cs.CRcs.LG