Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings
Zhejiang University（浙江大学）；ETH Zürich（苏黎世联邦理工学院）；Zhejiang University NGICS Platform（浙江大学NGICS平台）；Zhejiang Gongshang University（浙江工商大学）；Ant Group（蚂蚁集团）；Georgia Institute of Technology（佐治亚理工学院）；Pennsylvania State University（宾夕法尼亚州立大学）
Yuhao Mao, Chong Fu, Saizhuo Wang, Shouling Ji, Xuhong Zhang, Zhenguang Liu, Jun Zhou, Alex X. Liu, Raheem Beyah, Ting Wang
One intriguing property of adversarial attacks is their "transferability" -- an adversarial example crafted with respect to one deep neural network (DNN) model is often found effective against other DNNs as well. Intensive research has been conducted on this phenomenon under simplistic controlled conditions. Yet, thus far, there is still a lack of comprehensive understanding about transferability-based attacks ("transfer attacks") in real-world environments.
To bridge this critical gap, we conduct the first large-scale systematic empirical study of transfer attacks against major cloud-based MLaaS platforms, taking the components of a real transfer attack into account. The study leads to a number of interesting findings which are inconsistent to the existing ones, including: (1) Simple surrogates do not necessarily improve real transfer attacks. (2) No dominant surrogate architecture is found in real transfer attacks. (3) It is the gap between posterior (output of the softmax layer) rather than the gap between logit (so-called $κ$ value) that increases transferability. Moreover, by comparing with prior works, we demonstrate that transfer attacks possess many previously unknown properties in real-world environments, such as (1) Model similarity is not a well-defined concept. (2) $L_2$ norm of perturbation can generate high transferability without usage of gradient and is a more powerful source than $L_\infty$ norm. We believe this work sheds light on the vulnerabilities of popular MLaaS platforms and points to a few promising research directions.
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…
University of Western Australia（西澳大利亚大学）；University of Central Florida（中佛罗里达大学）
Deep Learning (DL) is the most widely used tool in the contemporary field of computer vision. Its ability to accurately solve complex problems is employed in vision research to learn deep neural models for a variety of tasks, including security critical applications. However, it is now known that DL is vulnerable to adversarial attacks that can manipulate its predictions by introducing visually imperceptible perturbations in images and videos. Since the discovery of this phenomenon in 2013~[1], it has attracted significant attention of researchers from multiple sub-fields of machine intelligen…
We provide a comprehensive overview of adversarial machine learning focusing on two application domains, i.e., cybersecurity and computer vision. Research in adversarial machine learning addresses a significant threat to the wide application of machine learning techniques -- they are vulnerable to carefully crafted attacks from malicious adversaries. For example, deep neural networks fail to correctly classify adversarial images, which are generated by adding imperceptible perturbations to clean images.We first discuss three main categories of attacks against machine learning techniques -- poi…
Delhi Technological University（德里理工大学）；Indraprastha Institute of Information Technology（英迪拉普拉萨信息技术学院）
Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life scenarios, pose a severe challenge to their applicability, pushing research into the direction which aims to enhance the robustness of these models. After the introduction of these perturbations by Szegedy et al. [1], significant amount of research has focused on the reliability of such models, primarily in two aspects - white-box, where the adversary has access…
Huazhong University of Science and Technology（华中科技大学）
Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately designed small perturbations are added to the benign input samples to fool the deep learning model and degrade its performance. This paper considers transferability-based black-box attacks, where the attacker trains a substitute model to approximate the target model, and then generates adversarial examples from the substitute model to attack the target model. Learn…
Recently it's been shown that neural networks can use images of human faces to accurately predict Body Mass Index (BMI), a widely used health indicator. In this paper we demonstrate that a neural network performing BMI inference is indeed vulnerable to test-time adversarial attacks. This extends test-time adversarial attacks from classification tasks to regression. The application we highlight is BMI inference in the insurance industry, where such adversarial attacks imply a danger of insurance fraud.
Deep learning is at the heart of the current rise of machine learning and artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, y…
A Survey on Physical Adversarial Attack in Computer Vision
Zhejiang University（浙江大学）；Defense Innovation Institute, Chinese Academy of Military Science（中国人民解放军军事科学院国防科技创新研究院）；National University of Defense Technology（国防科技大学）
Nanyang Technological University（南洋理工大学）；Harbin Institute of Technology（哈尔滨工业大学）；Carnegie Mellon University（卡内基梅隆大学）
Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks. Differentiable neural computer (DNC) is a novel computing machine with DNN as its central controller operating on an external memory module for data processing. The unique architecture of DNC contributes to its state-of-the-art performance in tasks which requires the ability to represent variables and data structure as well as to store data over long timescales. However, there still lacks a compreh…
Physical Adversarial Attack meets Computer Vision: A Decade Survey
Wuhan University（武汉大学）；Peking University（北京大学）；Zhejiang University（浙江大学）；National Institute of Informatics（情报通信研究机构）；The University of Tokyo（东京大学）；ETH Zurich（苏黎世联邦理工学院）；KU Leuven（鲁汶大学）；INSAIT
In the last decade, deep neural networks have proven to be very powerful in computer vision tasks, starting a revolution in the computer vision and machine learning fields. However, deep neural networks, usually, are not robust to perturbations of the input data. In fact, several studies showed that slightly changing the content of the images can cause a dramatic decrease in the accuracy of the attacked neural network. Several methods able to generate adversarial samples make use of gradients, which usually are not available to an attacker in real-world scenarios. As opposed to this class of a…
Department of Computer Science, University College London（伦敦大学学院计算机科学系）；Siemens Healthineers, Medical Imaging Technologies（西门子医疗，医学影像技术）
The design and performance of computer vision algorithms are greatly influenced by the hardware on which they are implemented. CPUs, multi-core CPUs, FPGAs and GPUs have inspired new algorithms and enabled existing ideas to be realized. This is notably the case with GPUs, which has significantly changed the landscape of computer vision research through deep learning. As the end of Moores law approaches, researchers and hardware manufacturers are exploring alternative hardware computing paradigms. Quantum computers are a very promising alternative and offer polynomial or even exponential speed-…
JAMK University of Applied Sciences（JAMK应用科学大学）；University of Jyväskylä（于韦斯屈莱大学）
Computer vision and machine learning can be used to automate various tasks in cancer diagnostic and detection. If an attacker can manipulate the automated processing, the results can be devastating and in the worst case lead to wrong diagnosis and treatment. In this research, the goal is to demonstrate the use of one-pixel attacks in a real-life scenario with a real pathology dataset, TUPAC16, which consists of digitized whole-slide images. We attack against the IBM CODAIT's MAX breast cancer detector using adversarial images. These adversarial examples are found using differential evolution t…
Center for Security and Emerging Technology, Georgetown University（乔治敦大学安全与新兴技术中心）；Georgetown University（乔治敦大学）
The resizing of images, which is typically a required part of preprocessing for computer vision systems, is vulnerable to attack. Images can be created such that the image is completely different at machine-vision scales than at other scales and the default settings for some common computer vision and machine learning systems are vulnerable. We show that defenses exist and are trivial to administer provided that defenders are aware of the threat. These attacks and defenses help to establish the role of input sanitization in machine learning.
University of Michigan（密歇根大学）；University of Wisconsin（威斯康星大学）
This paper investigates an adversary's ease of attack in generating adversarial examples for real-world scenarios. We address three key requirements for practical attacks for the real-world: 1) automatically constraining the size and shape of the attack so it can be applied with stickers, 2) transform-robustness, i.e., robustness of a attack to environmental physical variations such as viewpoint and lighting changes, and 3) supporting attacks in not only white-box, but also black-box hard-label scenarios, so that the adversary can attack proprietary models. In this work, we propose GRAPHITE, a…
University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
The increasing importance of both deep neural networks (DNNs) and cloud services for training them means that bad actors have more incentive and opportunity to insert backdoors to alter the behavior of trained models. In this paper, we introduce a novel method for backdoor detection that extracts features from pre-trained DNN's weights using independent vector analysis (IVA) followed by a machine learning classifier. In comparison to other detection techniques, this has a number of benefits, such as not requiring any training data, being applicable across domains, operating with a wide range o…
Network security has become an area of significant importance more than ever as highlighted by the eye-opening numbers of data breaches, attacks on critical infrastructure, and malware/ransomware/cryptojacker attacks that are reported almost every day. Increasingly, we are relying on networked infrastructure and with the advent of IoT, billions of devices will be connected to the internet, providing attackers with more opportunities to exploit. Traditional machine learning methods have been frequently used in the context of network security. However, such methods are more based on statistical …
Vision based object grasping and manipulation in robotics require accurate estimation of object's 6D pose. The 6D pose estimation has received significant attention in computer vision community and multiple datasets and evaluation metrics have been proposed. However, the existing metrics measure how well two geometrical surfaces are aligned - ground truth vs. estimated pose - which does not directly measure how well a robot can perform the task with the given estimate. In this work we propose a probabilistic metric that directly measures success in robotic tasks. The evaluation metric is based…
The convolutional neural network is the crucial tool for the recent success of deep learning based methods on various computer vision tasks like classification, segmentation, and detection. Convolutional neural networks achieved state-of-the-art performance in these tasks and every day pushing the limit of computer vision and AI. However, adversarial attack on computer vision systems is threatening their application in the real life and in safety-critical applications. Necessarily, Finding adversarial examples are important to detect susceptible models to attack and take safeguard measures to …
SOKENDAI (The Graduate University for Advanced Studies)（総合研究大学院大学（高等研究科大学院））；National Institute of Informatics（情报学研究所）；The University of Tokyo（东京大学）；The University of Edinburgh（爱丁堡大学）
The revolution in computer hardware, especially in graphics processing units and tensor processing units, has enabled significant advances in computer graphics and artificial intelligence algorithms. In addition to their many beneficial applications in daily life and business, computer-generated/manipulated images and videos can be used for malicious purposes that violate security systems, privacy, and social trust. The deepfake phenomenon and its variations enable a normal user to use his or her personal computer to easily create fake videos of anybody from a short real online video. Several …
