Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection
Army Engineering University of PLA（中国人民解放军陆军工程大学）；National University of Defense Technology（国防科技大学）；University Of Science & Technology Beijing（北京科技大学）；National Computer Network and Information Security Management Center（国家计算机网络与信息安全管理中心）；Shanghai Jiao Tong University（上海交通大学）
Sun RuiJin, Guo ShiZe, Guo JinHong, Xing ChangYou, Yang LuMing, Guo Xi, Pan ZhiSong
Deep neural networks (DNNs) are increasingly being applied in malware detection and their robustness has been widely debated. Traditionally an adversarial example generation scheme relies on either detailed model information (gradient-based methods) or lots of samples to train a surrogate model, neither of which are available in most scenarios.
We propose the notion of the instance-based attack. Our scheme is interpretable and can work in a black-box environment. Given a specific binary example and a malware classifier, we use the data augmentation strategies to produce enough data from which we can train a simple interpretable model. We explain the detection model by displaying the weight of different parts of the specific binary. By analyzing the explanations, we found that the data subsections play an important role in Windows PE malware detection. We proposed a new function preserving transformation algorithm that can be applied to data subsections. By employing the binary-diversification techniques that we proposed, we eliminated the influence of the most weighted part to generate adversarial examples. Our algorithm can fool the DNNs in certain cases with a success rate of nearly 100\%. Our method outperforms the state-of-the-art method . The most important aspect is that our method operates in black-box settings and the results can be validated with domain knowledge. Our analysis model can assist people in improving the robustness of malware detectors.
Anti-malware agents typically communicate with their remote services to share information about suspicious files. These remote services use their up-to-date information and global context (view) to help classify the files and instruct their agents to take a predetermined action (e.g., delete or quarantine). In this study, we provide a security analysis of a specific form of communication between anti-malware agents and their services, which takes place entirely over the insecure DNS protocol. These services, which we denote DNS anti-malware list (DNSAML) services, affect the classification of …
Nanjing University of Science and Technology（南京理工大学）；Florida International University（佛罗里达国际大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
Adversarial machine learning in the context of image processing and related applications has received a large amount of attention. However, adversarial machine learning, especially adversarial deep learning, in the context of malware detection has received much less attention despite its apparent importance. In this paper, we present a framework for enhancing the robustness of Deep Neural Networks (DNNs) against adversarial malware samples, dubbed Hashing Transformation Deep Neural Networks} (HashTran-DNN). The core idea is to use hash functions with a certain locality-preserving property to t…
Carnegie Mellon University（卡内基梅隆大学）；Tel Aviv University（特拉维夫大学）；VMware；Duke University（杜克大学）；NortonLifeLock Research Group（NortonLifeLock研究组）
Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes that do not require manual feature engineering. In this work, we propose an attack that interweaves binary-diversification techniques and optimization frameworks to mislead such DNNs while preserving the functionality of binaries. Unlike prior attacks, ours manipulates instructions that are a functional part of the binary, which makes it particularly challenging to defend against. We evaluated our attack against thr…
Macquarie University（麦考瑞大学）；University of Sydney（悉尼大学）
The vulnerability of smartphones to cyberattacks has been a severe concern to users arising from the integrity of installed applications (\textit{apps}). Although applications are to provide legitimate and diversified on-the-go services, harmful and dangerous ones have also uncovered the feasible way to penetrate smartphones for malicious behaviors. Thorough application analysis is key to revealing malicious intent and providing more insights into the application behavior for security risk assessments. Such in-depth analysis motivates employing deep neural networks (DNNs) for a set of features…
This work investigates three aspects: (a) a network vulnerability as the non-uniform vulnerable-host distribution, (b) threats, i.e., intelligent malwares that exploit such a vulnerability, and (c) defense, i.e., challenges for fighting the threats. We first study five large data sets and observe consistent clustered vulnerable-host distributions. We then present a new metric, referred to as the non-uniformity factor, which quantifies the unevenness of a vulnerable-host distribution. This metric is essentially the Renyi information entropy and better characterizes the non-uniformity of a distr…
Orange Innovation（Orange创新研究院）；University of Caen Normandy（卡昂诺曼底大学）
In addition to signature-based and heuristics-based detection techniques, machine learning (ML) is widely used to generalize to new, never-before-seen malicious software (malware). However, it has been demonstrated that ML models can be fooled by tricking the classifier into returning the incorrect label. These studies, for instance, usually rely on a prediction score that is fragile to gradient-based attacks. In the context of a more realistic situation where an attacker has very little information about the outputs of a malware detection engine, modest evasion rates are achieved. In this pap…
In this paper, we present a black-box attack against API call based machine learning malware classifiers, focusing on generating adversarial sequences combining API calls and static features (e.g., printable strings) that will be misclassified by the classifier without affecting the malware functionality. We show that this attack is effective against many classifiers due to the transferability principle between RNN variants, feed forward DNNs, and traditional machine learning classifiers such as SVM. We also implement GADGET, a software framework to convert any malware binary to a binary undet…
Machine-learning methods have already been exploited as useful tools for detecting malicious executable files. They leverage data retrieved from malware samples, such as header fields, instruction sequences, or even raw bytes, to learn models that discriminate between benign and malicious software. However, it has also been shown that machine learning and deep neural networks can be fooled by evasion attacks (also referred to as adversarial examples), i.e., small changes to the input data that cause misclassification at test time. In this work, we investigate the vulnerability of malware detec…
Machine learning based solutions have been very helpful in solving problems that deal with immense amounts of data, such as malware detection and classification. However, deep neural networks have been found to be vulnerable to adversarial examples, or inputs that have been purposefully perturbed to result in an incorrect label. Researchers have shown that this vulnerability can be exploited to create evasive malware samples. However, many proposed attacks do not generate an executable and instead generate a feature vector. To fully understand the impact of adversarial examples on malware dete…
LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges
Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；Beihang University（北京航空航天大学）；Beijing Jiaotong University（北京交通大学）；Northwestern Polytechnical University（西北工业大学）
Oregon State University（俄勒冈州立大学）；Google Brain（谷歌大脑）
Recent increases in the computational demands of deep neural networks (DNNs) have sparked interest in efficient deep learning mechanisms, e.g., quantization or pruning. These mechanisms enable the construction of a small, efficient version of commercial-scale models with comparable accuracy, accelerating their deployment to resource-constrained devices. In this paper, we study the security considerations of publishing on-device variants of large-scale models. We first show that an adversary can exploit on-device models to make attacking the large models easier. In evaluations across 19 DNNs, b…
Android malware is a persistent threat to billions of users around the world. As a countermeasure, Android malware detection systems are occasionally implemented. However, these systems are often vulnerable to \emph{evasion attacks}, in which an adversary manipulates malicious instances so that they are misidentified as benign. In this paper, we launch various innovative evasion attacks against several Android malware detection systems. The vulnerability inherent to all of these systems is that they are part of Androguard~\cite{desnos2011androguard}, a popular open source library used in Andro…
University of California at Santa Cruz（加州大学圣克鲁兹分校）；Microsoft Research（微软研究院）；Microsoft Corp.（微软公司）
Malicious software, or malware, presents a continuously evolving challenge in computer security. These embedded snippets of code in the form of malicious files or hidden within legitimate files cause a major risk to systems with their ability to run malicious command sequences. Malware authors even use polymorphism to reorder these commands and create several malicious variations. However, if executed in a secure environment, one can perform early malware detection on emulated command sequences. The models presented in this paper leverage this sequential data derived via emulation in order to …
During the past four years, Flash malware has become one of the most insidious threats to detect, with almost 600 critical vulnerabilities targeting Adobe Flash disclosed in the wild. Research has shown that machine learning can be successfully used to detect Flash malware by leveraging static analysis to extract information from the structure of the file or its bytecode. However, the robustness of Flash malware detectors against well-crafted evasion attempts - also known as adversarial examples - has never been investigated. In this paper, we propose a security evaluation of a novel, represen…
Centre for Computational Engineering and Networking (CEN), Amrita School of Engineering（阿姆里塔工程学院计算工程与网络中心（CEN））；Arnekt Solutions Pvt Ltd（Arnekt解决方案私人有限公司）；National Institute of Technology, Karnataka（卡纳塔克邦国家理工学院）
Deep neural networks (DNNs) have witnessed as a powerful approach in this year by solving long-standing Artificial intelligence (AI) supervised and unsupervised tasks exists in natural language processing, speech processing, computer vision and others. In this paper, we attempt to apply DNNs on three different cyber security use cases: Android malware classification, incident detection and fraud detection. The data set of each use case contains real known benign and malicious activities samples. The efficient network architecture for DNN is chosen by conducting various trails of experiments fo…
Recently, deep neural networks (DNNs) have been deployed in safety-critical systems such as autonomous vehicles and medical devices. Shortly after that, the vulnerability of DNNs were revealed by stealthy adversarial examples where crafted inputs -- by adding tiny perturbations to original inputs -- can lead a DNN to generate misclassification outputs. To improve the robustness of DNNs, some algorithmic-based countermeasures against adversarial examples have been introduced thereafter. In this paper, we propose a new type of stealthy attack on protected DNNs to circumvent the algorithmic defen…
Malware attacks are costly. To mitigate against such attacks, organizations deploy malware detection tools that help them detect and eventually resolve those threats. While running only the best available tool does not provide enough coverage of the potential attacks, running all available tools is prohibitively expensive in terms of financial cost and computing resources. Therefore, an organization typically runs a set of tools that maximizes their coverage given a limited budget. However, how should an organization choose that set? Attackers are strategic, and will change their behavior to p…
Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
Department of Computer Applications, Cochin University of Science and Technology（计算机应用系，科钦大学科学与技术学院）；Department of Electrical, Computer and Biomedical Engineering, University of Pavia（电气、计算机与生物医学工程系，帕维亚大学）
Due to the completely open-source nature of Android, the exploitable vulnerability of malware attacks is increasing. Machine learning, leading to a great evolution in Android malware detection in recent years, is typically applied in the classification phase. Since the correlation between features is ignored in some traditional ranking-based feature selection algorithms, applying wrapper-based feature selection models is a topic worth investigating. Though considering the correlation between features, wrapper-based approaches are time-consuming for exploring all possible valid feature subsets …
In recent years, the topic of explainable machine learning (ML) has been extensively researched. Up until now, this research focused on regular ML users use-cases such as debugging a ML model. This paper takes a different posture and show that adversaries can leverage explainable ML to bypass multi-feature types malware classifiers. Previous adversarial attacks against such classifiers only add new features and not modify existing ones to avoid harming the modified malware executable's functionality. Current attacks use a single algorithm that both selects which features to modify and modifies…
The wide acceptance of Internet of Things (IoT) for both household and industrial applications is accompanied by several security concerns. A major security concern is their probable abuse by adversaries towards their malicious intent. Understanding and analyzing IoT malicious behaviors is crucial, especially with their rapid growth and adoption in wide-range of applications. However, recent studies have shown that machine learning-based approaches are susceptible to adversarial attacks by adding junk codes to the binaries, for example, with an intention to fool those machine learning or deep …
Deep Learning is able to solve a plethora of once impossible problems. However, they are vulnerable to input adversarial attacks preventing them from being autonomously deployed in critical applications. Several algorithm-centered works have discussed methods to cause adversarial attacks and improve adversarial robustness of a Deep Neural Network (DNN). In this work, we elicit the advantages and vulnerabilities of hybrid 6T-8T memories to improve the adversarial robustness and cause adversarial attacks on DNNs. We show that bit-error noise in hybrid memories due to erroneous 6T-SRAM cells have…
Shiraz University of Technology（设拉子理工大学）；University of Padua（帕多瓦大学）
The widespread adoption of smartphones dramatically increases the risk of attacks and the spread of mobile malware, especially on the Android platform. Machine learning-based solutions have been already used as a tool to supersede signature-based anti-malware systems. However, malware authors leverage features from malicious and legitimate samples to estimate statistical difference in-order to create adversarial examples. Hence, to evaluate the vulnerability of machine learning algorithms in malware detection, we propose five different attack scenarios to perturb malicious applications (apps).…
Unraveling the Key of Machine Learning-based Android Malware Detection
National University of Singapore（新加坡国立大学）；University College London（伦敦大学学院）；The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）
Under the epidemic of the novel coronavirus disease 2019 (COVID-19), chest X-ray computed tomography imaging is being used for effectively screening COVID-19 patients. The development of computer-aided systems based on deep neural networks (DNNs) has been advanced, to rapidly and accurately detect COVID-19 cases, because the need for expert radiologists, who are limited in number, forms a bottleneck for the screening. However, so far, the vulnerability of DNN-based systems has been poorly evaluated, although DNNs are vulnerable to a single perturbation, called universal adversarial perturbatio…
Cybercrime markets support the development and diffusion of new attack technologies, vulnerability exploits, and malware. Whereas the revenue streams of cyber attackers have been studied multiple times in the literature, no quantitative account currently exists on the economics of attack acquisition and deployment. Yet, this understanding is critical to characterize the production of (traded) exploits, the economy that drives it, and its effects on the overall attack scenario. In this paper we provide an empirical investigation of the economics of vulnerability exploitation, and the effects of…
Michigan State University（密歇根州立大学）；Texas A&M University（得克萨斯农工大学）；IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）
Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability. Adversary can mislead GNNs to give wrong predictions by modifying the graph structure such as manipulating a few edges. This vulnerability has arisen tremendous concerns for adapting GNNs in safety-critical applications and has attracted increasing research attentio…
MEASER: Malware embedding attacks on open-source LLMs
Information Engineering University（信息工程大学）；Laboratory of Cyberspace Endogenous Security（网络空间内生安全实验室）；National Key Laboratory of advanced communication networks（先进通信网络国家重点实验室）；Key Laboratory of Cyberspace Security Ministry of Education of China（中国教育部网络空间安全重点实验室）；Henan Province Key Laboratory of Information Security（河南省信息安全重点实验室）；State Key Laboratory of Integrated Service Networks（集成服务网络国家重点实验室）；Institute of Mathematics and Interdisciplinary Sciences（数学与交叉科学研究院）
University of Chicago（芝加哥大学）；UC Berkeley（加州大学伯克利分校）；Cornell Tech（康奈尔科技校区）
Today, creators of data-hungry deep neural networks (DNNs) scour the Internet for training fodder, leaving users with little control over or knowledge of when their data is appropriated for model training. To empower users to counteract unwanted data use, we design, implement and evaluate a practical system that enables users to detect if their data was used to train an DNN model. We show how users can create special data points we call isotopes, which introduce "spurious features" into DNNs during training. With only query access to a trained model and no knowledge of the model training proce…
Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
Virelya Intelligence Research Labs（Virelya智能研究实验室）；Google（谷歌）
ByteDance AI Lab（字节跳动人工智能实验室）；University of California, Davis（加州大学戴维斯分校）
The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community. In this paper, we study the transferability of such examples, which lays the foundation of many black-box attacks on DNNs. We revisit a not so new but definitely noteworthy hypothesis of Goodfellow et al.'s and disclose that the transferability can be enhanced by improving the linearity of DNNs in an appropriate manner. We introduce linear backpropagation (LinBP), a method that performs backpropagation in a more linear fashion using off-the-shelf attacks that exploit gradients…
University of Science and Technology of China（中国科学技术大学）
Deep neural networks (DNNs) have achieved tremendous success in many tasks of machine learning, such as the image classification. Unfortunately, researchers have shown that DNNs are easily attacked by adversarial examples, slightly perturbed images which can mislead DNNs to give incorrect classification results. Such attack has seriously hampered the deployment of DNN systems in areas where security or safety requirements are strict, such as autonomous cars, face recognition, malware detection. Defensive distillation is a mechanism aimed at training a robust DNN which significantly reduces the…
Empowered by deep neural networks (DNNs), Wi-Fi fingerprinting has recently achieved astonishing localization performance to facilitate many security-critical applications in wireless networks, but it is inevitably exposed to adversarial attacks, where subtle perturbations can mislead DNNs to wrong predictions. Such vulnerability provides new security breaches to malicious devices for hampering wireless network security, such as malfunctioning geofencing or asset management. The prior adversarial attack on localization DNNs uses additive perturbations on channel state information (CSI) measure…
Towards Robust Model Watermark via Reducing Parametric Vulnerability
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Ant Group（蚂蚁集团）；The University of Tokyo（东京大学）；Peng Cheng Laboratory（鹏城实验室）
