Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines
GraphStax Research（GraphStax研究院）；Rotman School of Management - University of Toronto（多伦多大学罗特曼管理学院）；Creative Destruction Lab（创意破坏实验室）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）；Perimeter Institute for Theoretical Physics（圆周理论物理研究所）；Career Science Lab - BOSS Zhipin（BOSS直聘职业科学实验室）；Department of Mathematical Analysis - Universidad Complutense de Madrid（马德里康普顿斯大学数学分析系）
Aidan Kehoe, Peter Wittek, Yanbo Xue, Alejandro Pozas-Kerstjens
备注：
15 pages, 1 figure. V2: Updated to match published version
We provide a robust defence to adversarial attacks on discriminative algorithms. Neural networks are naturally vulnerable to small, tailored perturbations in the input data that lead to wrong predictions. On the contrary, generative models attempt to learn the distribution underlying a dataset, making them inherently more robust to small perturbations. We use Boltzmann machines for discrimination purposes as attack-resistant classifiers, and compare them against standard state-of-the-art adversarial defences. We find improvements ranging from 5% to 72% against attacks with Boltzmann machines on the MNIST dataset. We furthermore complement the training with quantum-enhanced sampling from the D-Wave 2000Q annealer, finding results comparable with classical techniques and with marginal improvements in some cases. These results underline the relevance of probabilistic methods in constructing neural networks and highlight a novel scenario of practical relevance where quantum computers, even with limited hardware capabilites, could provide advantages over classical computers. This work is dedicated to the memory of Peter Wittek.
In this paper, we propose a defence strategy to improve adversarial robustness by incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input information including adversarial perturbation. And this defence strategy can be regarded as an activation function which can be applied to any kind of neural network. We also prove theoretically the effectiveness of this defense strategy under certain conditions. Besides, incorporating hidden layer representation we propose three types of adversarial attacks to generate three types of adversarial examples…
IBM Research（IBM研究院）；University of Melbourne（墨尔本大学）
We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifie…
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been proposed in the recent years. However, most of the methods can only handle specific attacks. For example, proactive defending methods are invalid against grey-box or white-box attacks, while reactive defending methods are challenged by low-distortion adversarial examples or transferring adversarial examples. This becomes a critical problem since a defender usually does not have the …
University of Edinburgh（爱丁堡大学）；Samsung AI Center, Cambridge（三星剑桥人工智能中心）
This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult to navigate. A common, but not universal, way to achieve this effect is via the use of stochastic neural networks. We show that this is a form of gradient obfuscation, and propose a general extension to gradient-based adversaries based on the Weierstrass transform, which smooths the surface of the loss function and provides more reliable gradient estimates. We further show that…
Nirma University（尼尔玛大学）；Swiss School of Business and Management（瑞士商业与管理学院）；Bosch Global Software Technologies Pvt. Ltd.（博世全球软件技术私人有限公司）
From past couple of years there is a cycle of researchers proposing a defence model for adversaries in machine learning which is arguably defensible to most of the existing attacks in restricted condition (they evaluate on some bounded inputs or datasets). And then shortly another set of researcher finding the vulnerabilities in that defence model and breaking it by proposing a stronger attack model. Some common flaws are been noticed in the past defence models that were broken in very short time. Defence models being broken so easily is a point of concern as decision of many crucial activitie…
University of British Columbia（不列颠哥伦比亚大学）；University of Science and Technology of China（中国科学技术大学）；TrojAI Inc.（TrojAI公司）
Adversarial attacks in deep learning models, especially for safety-critical systems, are gaining more and more attention in recent years, due to the lack of trust in the security and robustness of AI models. Yet the more primitive adversarial attacks might be physically infeasible or require some resources that are hard to access like the training data, which motivated the emergence of patch attacks. In this survey, we provide a comprehensive overview to cover existing techniques of adversarial patch attacks, aiming to help interested researchers quickly catch up with the progress in this fiel…
In the last decade, deep learning algorithms have become very popular thanks to the achieved performance in many machine learning and computer vision tasks. However, most of the deep learning architectures are vulnerable to so called adversarial examples. This questions the security of deep neural networks (DNN) for many security- and trust-sensitive domains. The majority of the proposed existing adversarial attacks are based on the differentiability of the DNN cost function.Defence strategies are mostly based on machine learning and signal processing principles that either try to detect-rejec…
University of Liverpool（利物浦大学）；University of Oxford（牛津大学）；Lancaster University（兰卡斯特大学）；Defence Science and Technology Laboratory (Dstl)（国防科学技术实验室）；Queen’s University Belfast（贝尔法斯特女王大学）
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks. With the broader deployment of DNNs on various applications, the concerns over their safety and trustworthiness have been raised in public, especially after the widely reported fatal incidents involving self-driving cars. Research to address these concerns is particularly active, with a significant number of papers released in the past few years. This survey paper conducts a review of the current research effort into making DNNs safe and …
Google Brain（谷歌大脑）；Tsinghua University（清华大学）；The Johns Hopkins University（约翰斯·霍普金斯大学）；Baidu Research USA（百度美国研究院）；Snap Inc.（阅后即焚公司）；Sony Mobile Communications（索尼移动通信公司）；Microsoft corp.（微软公司）；Yale Univerisity（耶鲁大学）；Smule Inc.（斯穆尔公司）；Preferred Networks, Inc.（优选网络公司）
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop new ways to defend against them. In this chapter, we describe the structure and organization of the competition and the solutions developed by several of the top-placing teams.
Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to cause misclassification. The level of perturbation an attacker needs to introduce in order to cause such a misclassification can be extremely small, and often imperceptible. This is of significant security concern, particularly where misclassification can cause harm to humans. We thus propose Deep Latent Defence, an architecture which seeks to combine adversaria…
Kyushu University（九州大学）；Kyushu Institute of Technology（九州工业大学）
Neural networks have been shown vulnerable to a variety of adversarial algorithms. A crucial step to understanding the rationale for this lack of robustness is to assess the potential of the neural networks' representation to encode the existing features. Here, we propose a method to understand the representation quality of the neural networks using a novel test based on Zero-Shot Learning, entitled Raw Zero-Shot. The principal idea is that, if an algorithm learns rich features, such features should be able to interpret "unknown" classes as an aggregate of previously learned features. This is …
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…
Indian Institute of Technology, Kharagpur（印度理工学院卡拉格布尔分校）；The Ohio State University（俄亥俄州立大学）；Nanyang Technological University（南洋理工大学）
Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few years, deep learning has advanced radically in such a way that it can surpass human-level performance on a number of tasks. As a consequence, deep learning is being extensively used in most of the recent day-to-day applications. However, security of deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human …
University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
With the recent developments in artificial intelligence and machine learning, anomalies in network traffic can be detected using machine learning approaches. Before the rise of machine learning, network anomalies which could imply an attack, were detected using well-crafted rules. An attacker who has knowledge in the field of cyber-defence could make educated guesses to sometimes accurately predict which particular features of network traffic data the cyber-defence mechanism is looking at. With this information, the attacker can circumvent a rule-based cyber-defense system. However, after the …
There has been a concurrent significant improvement in the medical images used to facilitate diagnosis and the performance of machine learning techniques to perform tasks such as classification, detection, and segmentation in recent years. As a result, a rapid increase in the usage of such systems can be observed in the healthcare industry, for instance in the form of medical image classification systems, where these models have achieved diagnostic parity with human physicians. One such application where this can be observed is in computer vision tasks such as the classification of skin lesion…
We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several common adversarial attacks on CIFAR-$10$ classifiers for perturbations up to $ε= 8/255$ in $L_\infty$ norm and $ε= 0.5$ in $L_2$ norm. Implicit neural representations are used to approximately encode pixel colour intensities in $2\text{D}$ images such that classifiers trained on transformed data appear to have robustness to small perturbations without adversarial training or large drops in performance. The seed of the random number generator used to initialise a…
While many defences against adversarial examples have been proposed, finding robust machine learning models is still an open problem. The most compelling defence to date is adversarial training and consists of complementing the training data set with adversarial examples. Yet adversarial training severely impacts training time and depends on finding representative adversarial samples. In this paper we propose to train models on output spaces with large class separation in order to gain robustness without adversarial training. We introduce a method to partition the output space into class proto…
We propose a novel method for creating adversarial examples. Instead of perturbing pixels, we use an encoder-decoder representation of the input image and perturb intermediate layers in the decoder. This changes the high-level features provided by the generative model. Therefore, our perturbation possesses semantic meaning, such as a longer beak or green tints. We formulate this task as an optimization problem by minimizing the Wasserstein distance between the adversarial and initial images under a misclassification constraint. We employ the projected gradient method with a simple inexact proj…
There exists a vast number of adversarial attacks and defences for machine learning algorithms of various types which makes assessing the robustness of algorithms a daunting task. To make matters worse, there is an intrinsic bias in these adversarial algorithms. Here, we organise the problems faced: a) Model Dependence, b) Insufficient Evaluation, c) False Adversarial Samples, and d) Perturbation Dependent Results). Based on this, we propose a model agnostic dual quality assessment method, together with the concept of robustness levels to tackle them. We validate the dual quality assessment on…
The Department of Computer Science, The University of Western Australia（西澳大学计算机科学系）
Deep learning offers state of the art solutions for image recognition. However, deep models are vulnerable to adversarial perturbations in images that are subtle but significantly change the model's prediction. In a white-box attack, these perturbations are generally learned for deep models that operate on RGB images and, hence, the perturbations are equally distributed in the RGB color space. In this paper, we show that the adversarial perturbations prevail in the Y-channel of the YCbCr space. Our finding is motivated from the fact that the human vision and deep models are more responsive to …
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
In this work, we evaluate adversarial robustness in the context of transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10. Specifically, we study the effects of using robust optimisation in the source and target networks. This allows us to identify transfer learning strategies under which adversarial defences are successfully retained, in addition to revealing potential vulnerabilities. We study the extent to which features learnt by a fast gradient sign method (FGSM) and its iterative alternative (PGD) can preserve their defence properties against black a…
Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算中心（国家超级计算济南中心））；Nanyang Technological University（南洋理工大学）
Whereas adversarial training is employed as the main defence strategy against specific adversarial samples, it has limited generalization capability and incurs excessive time complexity. In this paper, we propose an attack-agnostic defence framework to enhance the intrinsic robustness of neural networks, without jeopardizing the ability of generalizing clean samples. Our Feature Pyramid Decoder (FPD) framework applies to all block-based convolutional neural networks (CNNs). It implants denoising and image restoration modules into a targeted CNN, and it also constraints the Lipschitz constant o…
Skoltech（斯科尔科沃科学技术学院）；IITP RAS（俄罗斯科学院信息传输问题研究所）；MIPT（莫斯科物理技术学院）；Sber AI lab（俄罗斯联邦储蓄银行人工智能实验室）
Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their tremendous number of parameters and limited robustness. In particular, deep-learning models are vulnerable to adversarial attacks: a little change in the input harms the model's output. In this work, we examine adversarial attacks on transaction records data and defences from these attacks. The transaction records data have a different structure than the canonical NL…
Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against adversarial attacks without prior training on adversarial samples. We propose a test-time adversarial example detector which detects the input adversarial example through quantifying the localized intermediate responses of a pre-trained neural network and confidence scores of an auxiliary softmax layer. Furthermore, in order to make the network robust, we extenuate the non-relevant features by non-iterative input sam…
Federal Office for Information Security（德国联邦信息安全办公室）
This article deals with the IT security of connectionist artificial intelligence (AI) applications, focusing on threats to integrity, one of the three IT security goals. Such threats are for instance most relevant in prominent AI computer vision applications. In order to present a holistic view on the IT security goal integrity, many additional aspects such as interpretability, robustness and documentation are taken into account. A comprehensive list of threats and possible mitigations is presented by reviewing the state-of-the-art literature. AI-specific vulnerabilities such as adversarial at…
Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains. However, just like other neural network models, they suffer from a susceptibility to noise and adversarial attacks. An adversarial defence aims at reducing a neural network's susceptibility to adversarial attacks through learning or architectural modifications. We propose the weight map layer (WM) as a generic architectural addition to CNNs and show that it can increase their robustness to noise and…
With machine learning models being used for more sensitive applications, we rely on interpretability methods to prove that no discriminating attributes were used for classification. A potential concern is the so-called "fair-washing" - manipulating a model such that the features used in reality are hidden and more innocuous features are shown to be important instead. In our work we present an effective defence against such adversarial attacks on neural networks. By a simple aggregation of multiple explanation methods, the network becomes robust against manipulation. This holds even when the at…
Microsoft Research Cambridge（微软研究院剑桥分院）；University of Cambridge（剑桥大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Eberhard Karls University of Tübingen（图宾根大学）
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative classifiers, which only model the conditional distribution of the labels given the inputs. In this paper, we propose and investigate the deep Bayes classifier, which improves classical naive Bayes with conditional deep generative models. We further develop detection methods for adversarial examples, which reject inputs with low likelihood under the generative m…
We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a two-player zero-sum game. In this new formulation, both players simultaneously play the same game, where one player chooses a classifier that minimizes a classification loss whilst the other player creates an adversarial perturbation that increases the same loss when applied to every sample in the training set. By observing that performing a classification (respectiv…
IBM Research Europe（IBM欧洲研究院）；Imperial College London（伦敦帝国学院）
In federated learning (FL), robust aggregation schemes have been developed to protect against malicious clients. Many robust aggregation schemes rely on certain numbers of benign clients being present in a quorum of workers. This can be hard to guarantee when clients can join at will, or join based on factors such as idle system status, and connected to power and WiFi. We tackle the scenario of securing FL systems conducting adversarial training when a quorum of workers could be completely malicious. We model an attacker who poisons the model to insert a weakness into the adversarial training …
University of Torino（都灵大学）；Collegio Carlo Alberto（卡洛·阿尔贝托学院）；Reale Mutua Group（瑞莱穆图阿集团）；KPA Group（KPA集团）；Samuel Neaman Institute（塞缪尔·尼曼研究所）；Technion（以色列理工学院）
The rapid and dynamic pace of Artificial Intelligence (AI) and Machine Learning (ML) is revolutionizing the insurance sector. AI offers significant, very much welcome advantages to insurance companies, and is fundamental to their customer-centricity strategy. It also poses challenges, in the project and implementation phase. Among those, we study Adversarial Attacks, which consist of the creation of modified input data to deceive an AI system and produce false outputs. We provide examples of attacks on insurance AI applications, categorize them, and argue on defence methods and precautionary s…
Imperial College London（帝国理工学院）；IBM Research（IBM研究院）
Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as the most promising approach against evasion threats on ML models. In this paper, we take the first known steps towards federated adversarial training (FAT) combining both methods to reduce the threat of evasion during inference while preserving the data privacy during training. We investigate the effectiveness of the FAT protocol for idealised federated settings using MNIST, Fashion-MNIST, and CIFAR10, and provide fi…
Monash University（莫纳什大学）；Defence Science and Technology Group, Department of Defence（国防部国防科学与技术集团）
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been proposed, most of which focus on adding small perturbations to input images. Despite the success of existing approaches, the way to generate realistic adversarial images with small perturbations remains a challenging problem. In this paper, we aim to address this problem by proposing a novel adversarial method, which generates adversarial examples by imposing not o…
iFLYTEK Laboratory for Neural Computing and Machine Learning (iNCML)（科大讯飞神经计算与机器学习实验室（iNCML））；York University（约克大学）
In this paper, we study the adversarial attack and defence problem in deep learning from the perspective of Fourier analysis. We first explicitly compute the Fourier transform of deep ReLU neural networks and show that there exist decaying but non-zero high frequency components in the Fourier spectrum of neural networks. We demonstrate that the vulnerability of neural networks towards adversarial samples can be attributed to these insignificant but non-zero high frequency components. Based on this analysis, we propose to use a simple post-averaging technique to smooth out these high frequency …
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms to extract valuable information from data and produce accurate predictions, it has been shown that these algorithms are vulnerable to attacks. Data poisoning is one of the most relevant security threats against machine learning systems, where attackers can subvert the learning process by injecting malicious samples in the training data. Recent work in adversa…
Macquarie University（麦考瑞大学）；The University of Adelaide（阿德莱德大学）
Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly expressive deep classifiers into incorrect predictions. Approaches to adversarial attacks in natural language tasks have boomed in the last five years using character-level, word-level, phrase-level, or sentence-level textual perturbations. While there is some work in NLP on defending against such attacks through proactive methods, like adversarial training,…
A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs
Kasimir Tanner Information Learning and Physics Laboratory, École Polytechnique Fédérale de Lausanne (EPFL)（信息学习与物理实验室，瑞士联邦理工学院（EPFL））；Matteo Vilucchio Information Learning and Physics Laboratory, École Polytechnique Fédérale de Lausanne (EPFL)（信息学习与物理实验室，瑞士联邦理工学院（EPFL））；Bruno Loureiro Departement d’Informatique, École Normale Supérieure, PSL & CNRS（信息系，巴黎高等师范学院，PSL与CNRS）；Florent Krzakala Information Learning and Physics Laboratory, École Polytechnique Fédérale de Lausanne (EPFL)（信息学习与物理实验室，瑞士联邦理工学院（EPFL））
IBM Research（IBM研究院）；Univ Lyon（里昂大学）；UJM-Saint-Etienne（圣艾蒂安让·莫内大学）；CNRS（法国国家科学研究中心）；Institut d Optique Graduate School（高等光学学校）
Adversarial Robustness Toolbox (ART) is a Python library supporting developers and researchers in defending Machine Learning models (Deep Neural Networks, Gradient Boosted Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, Gaussian Processes, Decision Trees, Scikit-learn Pipelines, etc.) against adversarial threats and helps making AI systems more secure and trustworthy. Machine Learning models are vulnerable to adversarial examples, which are inputs (images, texts, tabular data, etc.) deliberately modified to produce a desired response by the Machine Learning model.…
Saarland University（萨尔兰大学）；University of Tübingen（图宾根大学）
It has recently been shown that neural networks but also other classifiers are vulnerable to so called adversarial attacks e.g. in object recognition an almost non-perceivable change of the image changes the decision of the classifier. Relatively fast heuristics have been proposed to produce these adversarial inputs but the problem of finding the optimal adversarial input, that is with the minimal change of the input, is NP-hard. While methods based on mixed-integer optimization which find the optimal adversarial input have been developed, they do not scale to large networks. Currently, the at…
