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, an efficient and general framework for generating attacks that satisfy the above three key requirements. GRAPHITE takes advantage of transform-robustness, a metric based on expectation over transforms (EoT), to automatically generate small masks and optimize with gradient-free optimization. GRAPHITE is also flexible as it can easily trade-off transform-robustness, perturbation size, and query count in black-box settings. On a GTSRB model in a hard-label black-box setting, we are able to find attacks on all possible 1,806 victim-target class pairs with averages of 77.8% transform-robustness, perturbation size of 16.63% of the victim images, and 126K queries per pair. For digital-only attacks where achieving transform-robustness is not a requirement, GRAPHITE is able to find successful small-patch attacks with an average of only 566 queries for 92.2% of victim-target pairs. GRAPHITE is also able to find successful attacks using perturbations that modify small areas of the input image against PatchGuard, a recently proposed defense against patch-based attacks.
Security of automatic speaker verification (ASV) systems is compromised by various spoofing attacks. While many types of non-proactive attacks (and their defenses) have been studied in the past, attacker's perspective on ASV, represents a far less explored direction. It can potentially help to identify the weakest parts of ASV systems and be used to develop attacker-aware systems. We present an overview on this emerging research area by focusing on potential threats of adversarial attacks on ASV, spoofing countermeasures, or both. We conclude the study with discussion on selected attacks and l…
Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology（南方科技大学可信自主系统研究院）；Southern University of Science and Technology（南方科技大学）
Attack Ensemble (AE), which combines multiple attacks together, provides a reliable way to evaluate adversarial robustness. In practice, AEs are often constructed and tuned by human experts, which however tends to be sub-optimal and time-consuming. In this work, we present AutoAE, a conceptually simple approach for automatically constructing AEs. In brief, AutoAE repeatedly adds the attack and its iteration steps to the ensemble that maximizes ensemble improvement per additional iteration consumed. We show theoretically that AutoAE yields AEs provably within a constant factor of the optimal fo…
IBM Research（IBM研究院）；University of Copenhagen（哥本哈根大学）
Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains. Both black-box and white-box approaches have been used to either replicate the model itself or to craft examples which cause the model to fail. In this work, we propose a framework which uses multi-objective evolutionary optimization to perform both targeted and un-targeted black-box attacks on Automatic Speech Recognition (ASR) systems. We apply this framework on two ASR systems: Deepspeech and Kaldi-ASR, which increases the Word Error Rates…
The University of Tokyo（东京大学）；Nippon Telegraph and Telephone Corporation（日本电报电话公司）
This paper presents a new voice impersonation attack using voice conversion (VC). Enrolling personal voices for automatic speaker verification (ASV) offers natural and flexible biometric authentication systems. Basically, the ASV systems do not include the users' voice data. However, if the ASV system is unexpectedly exposed and hacked by a malicious attacker, there is a risk that the attacker will use VC techniques to reproduce the enrolled user's voices. We name this the ``verification-to-synthesis (V2S) attack'' and propose VC training with the ASV and pre-trained automatic speech recogniti…
Popular instant messaging applications such as WhatsApp and Signal provide end-to-end encryption for billions of users. They rely on a centralized, application-specific server to distribute public keys and relay encrypted messages between the users. Therefore, they prevent passive attacks but are vulnerable to some active attacks. A malicious or hacked server can distribute fake keys to users to perform man-in-the-middle or impersonation attacks. While typical secure messaging applications provide a manual method for users to detect these attacks, this burdens users, and studies show it is ine…
University of Florida（佛罗里达大学）；University of Toronto（多伦多大学）
Speech and speaker recognition systems are employed in a variety of applications, from personal assistants to telephony surveillance and biometric authentication. The wide deployment of these systems has been made possible by the improved accuracy in neural networks. Like other systems based on neural networks, recent research has demonstrated that speech and speaker recognition systems are vulnerable to attacks using manipulated inputs. However, as we demonstrate in this paper, the end-to-end architecture of speech and speaker systems and the nature of their inputs make attacks and defenses a…
Artificial intelligence (AI) technology has provided a potential solution for automatic modulation recognition (AMC). Unfortunately, AI-based AMC models are vulnerable to adversarial examples, which seriously threatens the efficient, secure and trusted application of AI in AMC. This issue has attracted the attention of researchers. Various studies on adversarial attacks and defenses evolve in a spiral. However, the existing adversarial attack methods are all designed in the time domain. They introduce more high-frequency components in the frequency domain, due to abrupt updates in the time dom…
Objective. Insecure Direct Object Reference (IDOR) or Broken Object Level Authorization (BOLA) are one of the critical type of access control vulnerabilities for modern applications. As a result, an attacker can bypass authorization checks leading to information leakage, account takeover. Our main research goal was to help an application security architect to optimize security design and testing process by giving an algorithm and tool that allows to automatically analyze system API specifications and generate list of possible vulnerabilities and attack vector ready to be used as security non-f…
University of Cagliari（卡利亚里大学）；Pluribus One；University of Genoa（热那亚大学）；Google（谷歌）；CINI（意大利国家信息学大学联盟）
Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of robustness by causing gradient-based attacks to fail, and they have been broken under more rigorous evaluations. Although guidelines and best practices have been suggested to improve current adversarial robustness evaluations, the lack of automatic testing and debugging tools makes it difficult to apply these recommendations in a systematic manner. In this work, we overcome these limitations by: (i) categorizing attack failures based on ho…
Automatic speech recognition (ASR) systems have been widely deployed in modern smart devices to provide convenient and diverse voice-controlled services. Since ASR systems are vulnerable to audio replay attacks that can spoof and mislead ASR systems, a number of defense systems have been proposed to identify replayed audio signals based on the speakers' unique acoustic features in the frequency domain. In this paper, we uncover a new type of replay attack called modulated replay attack, which can bypass the existing frequency domain based defense systems. The basic idea is to compensate for th…
Automatic Adjustment of HPA Parameters and Attack Prevention in Kubernetes Using Random Forests
School of Computer Sciences, Universiti Sains Malaysia（计算机科学学院，马来西亚理科大学）；Xiamen Institute of Software Technology, China（厦门软件技术研究所，中国）；Information Management Department of Manzhouli Customs, China（满洲里海关信息管理部，中国）；College of Information Science and Engineering, Jimei University, China（信息科学与工程学院，嘉义大学）
The side-channel attack is an attack method based on the information gained about implementations of computer systems, rather than weaknesses in algorithms. Information about system characteristics such as power consumption, electromagnetic leaks and sound can be exploited by the side-channel attack to compromise the system. Much research effort has been directed towards this field. However, such an attack still requires strong skills, thus can only be performed effectively by experts. Here, we propose SCNet, which automatically performs side-channel attacks. And we also design this network co…
University of Eastern Finland（东芬兰大学）；NEC（日本电气股份有限公司）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林信息学及其应用研究实验室）
In this work, we simulate a scenario, where a publicly available ASV system is used to enhance mimicry attacks against another closed source ASV system. In specific, ASV technology is used to perform a similarity search between the voices of recruited attackers (6) and potential target speakers (7,365) from VoxCeleb corpora to find the closest targets for each of the attackers. In addition, we consider 'median', 'furthest', and 'common' targets to serve as a reference points. Our goal is to gain insights how well similarity rankings transfer from the attacker's ASV system to the attacked ASV s…
Audio CAPTCHAs are supposed to provide a strong defense for online resources; however, advances in speech-to-text mechanisms have rendered these defenses ineffective. Audio CAPTCHAs cannot simply be abandoned, as they are specifically named by the W3C as important enablers of accessibility. Accordingly, demonstrably more robust audio CAPTCHAs are important to the future of a secure and accessible Web. We look to recent literature on attacks on speech-to-text systems for inspiration for the construction of robust, principle-driven audio defenses. We begin by comparing 20 recent attack papers, c…
SynAT: Enhancing Security Knowledge Bases via Automatic Synthesizing Attack Tree from Crowd Discussions
State Key Laboratory of Intelligent Game（智能游戏国家重点实验室）；Science and Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences（中国科学院软件研究所集成信息系统重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；School of Software, Beihang University（北京航空航天大学软件学院）；School of Information Technology and Electrical Engineering, The University of Queensland（昆士兰大学信息技术与电气工程学院）；Huawei Cloud Computing Technologies CO., LTD.（华为云计算技术有限公司）
Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction between humans and machines. Recently, researchers have demonstrated powerful attacks against machine learning models that can fool them to produceincorrect results. However, nearly all previous research in adversarial attacks has focused on image recognition and object detection models. In this short paper, we present a first of its kind demonstration of adve…
University of Washington（华盛顿大学）；Worcester Polytechnic Institute（伍斯特理工学院）
Due to the growth of video data on Internet, automatic video analysis has gained a lot of attention from academia as well as companies such as Facebook, Twitter and Google. In this paper, we examine the robustness of video analysis algorithms in adversarial settings. Specifically, we propose targeted attacks on two fundamental classes of video analysis algorithms, namely video classification and shot detection. We show that an adversary can subtly manipulate a video in such a way that a human observer would perceive the content of the original video, but the video analysis algorithm will retur…
ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs
State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou（杭州高新区（滨江）区块链与数据安全研究院，杭州）；College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）
Fraunhofer AISEC（弗劳恩霍夫人工智能安全研究所）；Technical University Munich（慕尼黑工业大学）
Model inversion (MI) attacks allow to reconstruct average per-class representations of a machine learning (ML) model's training data. It has been shown that in scenarios where each class corresponds to a different individual, such as face classifiers, this represents a severe privacy risk. In this work, we explore a new application for MI: the extraction of speakers' voices from a speaker recognition system. We present an approach to (1) reconstruct audio samples from a trained ML model and (2) extract intermediate voice feature representations which provide valuable insights into the speakers…
Avignon Université（阿维尼翁大学）；Université de Lille（里尔大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Centrale Lille（里尔中央理工学院）
This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR). This problem is especially important in the context of federated learning of ASR acoustic models where a global model is learnt on the server based on the updates received from multiple clients. We propose an approach to analyze information in neural network AMs based on a neural network footprint on the so-called Indicator dataset. Using this method, we develop two attack models that aim to infer speaker i…
Ruhr University Bochum（波鸿鲁尔大学）；International Computer Science Institute (ICSI)（国际计算机科学研究所）；Technische Universität Berlin（柏林工业大学）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
The number of papers submitted to academic conferences is steadily rising in many scientific disciplines. To handle this growth, systems for automatic paper-reviewer assignments are increasingly used during the reviewing process. These systems use statistical topic models to characterize the content of submissions and automate the assignment to reviewers. In this paper, we show that this automation can be manipulated using adversarial learning. We propose an attack that adapts a given paper so that it misleads the assignment and selects its own reviewers. Our attack is based on a novel optimiz…
University of Chicago（芝加哥大学）；University of Florida（佛罗里达大学）
An adversarial attack is an exploitative process in which minute alterations are made to natural inputs, causing the inputs to be misclassified by neural models. In the field of speech recognition, this has become an issue of increasing significance. Although adversarial attacks were originally introduced in computer vision, they have since infiltrated the realm of speech recognition. In 2017, a genetic attack was shown to be quite potent against the Speech Commands Model. Limited-vocabulary speech classifiers, such as the Speech Commands Model, are used in a variety of applications, particula…
Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
Beijing University of Posts and Telecommunications（北京邮电大学）；Tsinghua University（清华大学）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61）；Nanyang Technological University（南洋理工大学）
National Taiwan University of Science and Technology（台湾科技大学）；Academia Sinica（中央研究院）
Web applications suffer from cross-site scripting (XSS) attacks that resulting from incomplete or incorrect input sanitization. Learning the structure of attack vectors could enrich the variety of manifestations in generated XSS attacks. In this study, we focus on generating more threatening XSS attacks for the state-of-the-art detection approaches that can find potential XSS vulnerabilities in Web applications, and propose a mechanism for structural learning of attack vectors with the aim of generating mutated XSS attacks in a fully automatic way. Mutated XSS attack generation depends on the …
Tubes Among Us: Analog Attack on Automatic Speaker Identification
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Alan Turing Institute（艾伦·图灵研究所）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Oxford（牛津大学）
Due to the current horizontal business model that promotes increasing reliance on untrusted third-party Intellectual Properties (IPs), CAD tools, and design facilities, hardware Trojan attacks have become a serious threat to the semiconductor industry. Development of effective countermeasures against hardware Trojan attacks requires: (1) fast and reliable exploration of the viable Trojan attack space for a given design and (2) a suite of high-quality Trojan-inserted benchmarks that meet specific standards. The latter has become essential for the development and evaluation of design/verificatio…
We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per second of audio). We apply our white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.
The security of modern electronic devices relies on secret keys stored on secure hardware modules as the root-of-trust (RoT). Extracting those keys would break the security of the entire system. As shown before, sophisticated side-channel analysis (SCA) attacks, using chip failure analysis (FA) techniques, can extract data from on-chip memory cells. However, since the chip's layout is unknown to the adversary in practice, secret key localization and reverse engineering are onerous tasks. Consequently, hardware vendors commonly believe that the ever-growing physical complexity of the integrated…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Mayachitra Inc（玛雅奇特拉公司）
Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind these adversarial machine learning attacks will aid in recovering the tools and processes used in these attacks. In this paper, we present two techniques that support automated identification and attribution of adversarial ML attack toolchains using Co-occurrence Pixel statistics and Laplacian Residuals. Our experiments show that the proposed techniques can identify parameters used to generate adversarial samples. To t…
Shandong University（山东大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Boston University（波士顿大学）；Indiana University Bloomington（印第安纳大学伯明顿分校）
With the wide use of Automatic Speech Recognition (ASR) in applications such as human machine interaction, simultaneous interpretation, audio transcription, etc., its security protection becomes increasingly important. Although recent studies have brought to light the weaknesses of popular ASR systems that enable out-of-band signal attack, adversarial attack, etc., and further proposed various remedies (signal smoothing, adversarial training, etc.), a systematic understanding of ASR security (both attacks and defenses) is still missing, especially on how realistic such threats are and how gene…
Spoofing attacks posed by generating artificial speech can severely degrade the performance of a speaker verification system. Recently, many anti-spoofing countermeasures have been proposed for detecting varying types of attacks from synthetic speech to replay presentations. While there are numerous effective defenses reported on standalone anti-spoofing solutions, the integration for speaker verification and spoofing detection systems has obvious benefits. In this paper, we propose a spoofing-robust automatic speaker verification (SR-ASV) system for diverse attacks based on a multi-task learn…
An increasing number of Internet of Things (IoT) devices are connecting to the Internet, yet many of these devices are fundamentally insecure, exposing the Internet to a variety of attacks. Botnets such as Mirai have used insecure consumer IoT devices to conduct distributed denial of service (DDoS) attacks on critical Internet infrastructure. This motivates the development of new techniques to automatically detect consumer IoT attack traffic. In this paper, we demonstrate that using IoT-specific network behaviors (e.g. limited number of endpoints and regular time intervals between packets) to …
Horst Görtz Institute for IT Security（霍斯特·格茨信息技术安全研究所）；Ruhr-Universität Bochum（波鸿鲁尔大学）
Voice interfaces are becoming accepted widely as input methods for a diverse set of devices. This development is driven by rapid improvements in automatic speech recognition (ASR), which now performs on par with human listening in many tasks. These improvements base on an ongoing evolution of DNNs as the computational core of ASR. However, recent research results show that DNNs are vulnerable to adversarial perturbations, which allow attackers to force the transcription into a malicious output. In this paper, we introduce a new type of adversarial examples based on psychoacoustic hiding. Our a…
Automatic speech recognition (ASR) systems can be fooled via targeted adversarial examples, which induce the ASR to produce arbitrary transcriptions in response to altered audio signals. However, state-of-the-art adversarial examples typically have to be fed into the ASR system directly, and are not successful when played in a room. The few published over-the-air adversarial examples fall into one of three categories: they are either handcrafted examples, they are so conspicuous that human listeners can easily recognize the target transcription once they are alerted to its content, or they req…
Attack Rules: An Adversarial Approach to Generate Attacks for Industrial Control Systems using Machine Learning
DHA Suffa University（DHA Suffa大学）；University of Strathclyde（斯特拉斯克莱德大学）；Karachi Institute of Economics and Technology（卡拉奇经济与技术学院）；Singapore University of Technology and Design（新加坡科技设计大学）
It is challenging for a security analyst to detect or defend against cyber-attacks. Moreover, traditional defense deployment methods require the security analyst to manually enforce the defenses in the presence of uncertainties about the defense to deploy. As a result, it is essential to develop an automated and resilient defense deployment mechanism to thwart the new generation of attacks. In this paper, we propose a framework based on Markov Decision Process (MDP) and Q-learning to automatically generate optimal defense solutions for networked system states. The framework consists of four ph…
Zhejiang Lab（之江实验室）；National Research Centre of Parallel Computer Engineering and Technology（国家并行计算机工程技术研究中心）
Penetration Testing plays a critical role in evaluating the security of a target network by emulating real active adversaries. Deep Reinforcement Learning (RL) is seen as a promising solution to automating the process of penetration tests by reducing human effort and improving reliability. Existing RL solutions focus on finding a specific attack path to impact the target hosts. However, in reality, a diverse range of attack variations are needed to provide comprehensive assessments of the target network's security level. Hence, the attack agents must consider multiple objectives when penetrati…
Large Language Model-Based Framework for Explainable Cyberattack Detection in Automatic Generation Control Systems
Department of Computer Science, College of Computing and Mathematical Sciences, Khalifa University（计算机科学系，计算与数学科学学院，哈利法大学）；ECE Department, University of Toronto（电子工程系，多伦多大学）；Concordia Institute for Information Systems Engineering (CIISE), Concordia University（信息系统工程研究所（CIISE），康科迪亚大学）；Department of Electrical Engineering, College of Engineering and Physical Sciences, Khalifa University（电气工程系，工程与物理科学学院，哈利法大学）
