Biblio

Manufacturers often buy and/or license communication ICs from third-party suppliers. These communication ICs are then integrated into a complex computational system, resulting in a wide range of potential hardware-software security issues. This work proposes a compact supervisory circuit to classify the Bluetooth profile operation of a Bluetooth System-on-Chip (SoC) at low frequencies by monitoring the radio frequency (RF) output power of the Bluetooth SoC. The idea is to inexpensively manufacture an RF envelope detector to monitor the RF output power and a profile classification algorithm on a custom low-frequency integrated circuit in a low-cost legacy technology. When the supervisory circuit observes unexpected behavior, it can shut off power to the Bluetooth SoC. In this preliminary work, we proto-type the supervisory circuit using off-the-shelf components to collect a sufficient data set to train 11 different Machine Learning models. We extract smart descriptive time-domain features from the envelope of the RF output signal. Then, we train the machine learning models to classify three different Bluetooth operation profiles: sensor, hands-free, and headset. Our results demonstrate 100% classification accuracy with low computational complexity.

Twitter being the most popular content sharing platform is giving rise to automated accounts called “bots”. Majority of the users on Twitter are bots. Various machine learning (ML) algorithms are designed to detect bots avoiding the vulnerability constraints of ML-based models. This paper contributes to exploit vulnerabilities of machine learning (ML) algorithms through black-box attack. An adversarial text sequence misclassifies the results of deep learning (DL) classifiers for bot detection. Literature shows that ML models are vulnerable to attacks. The aim of this paper is to compromise the accuracy of ML-based bot detection algorithms by replacing original words in tweets with their synonyms. Our results show 7.2% decrease in the accuracy for bot tweets, therefore classifying bot tweets as legitimate tweets.

Generating adversarial samples is gathering much attention as an intuitive approach to evaluate the robustness of learning models. Extensive recent works have demonstrated that numerous advanced image classifiers are defenseless to adversarial perturbations in the white-box setting. However, the white-box setting assumes attackers to have prior knowledge of model parameters, which are generally inaccessible in real world cases. In this paper, we concentrate on the hard-label black-box setting where attackers can only pose queries to probe the model parameters responsible for classifying different images. Therefore, the issue is converted into minimizing non-continuous function. A black-box approach is proposed to address both massive queries and the non-continuous step function problem by applying a combination of a linear fine-grained search, Fibonacci search, and a zeroth order optimization algorithm. However, the input dimension of a image is so high that the estimation of gradient is noisy. Hence, we adopt a zeroth-order optimization method in high dimensions. The approach converts calculation of gradient into a linear regression model and extracts dimensions that are more significant. Experimental results illustrate that our approach can relatively reduce the amount of queries and effectively accelerate convergence of the optimization method.

Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations. Despite the long-term vision, however, existing studies on black-box adversarial attacks are still restricted to very specific settings of threat models (e.g., single distortion metric and restrictive assumption on target model's feedback to queries) and/or suffer from prohibitively high query complexity. To push for further advances in this field, we introduce a general framework based on an operator splitting method, the alternating direction method of multipliers (ADMM) to devise efficient, robust black-box attacks that work with various distortion metrics and feedback settings without incurring high query complexity. Due to the black-box nature of the threat model, the proposed ADMM solution framework is integrated with zeroth-order (ZO) optimization and Bayesian optimization (BO), and thus is applicable to the gradient-free regime. This results in two new black-box adversarial attack generation methods, ZO-ADMM and BO-ADMM. Our empirical evaluations on image classification datasets show that our proposed approaches have much lower function query complexities compared to state-of-the-art attack methods, but achieve very competitive attack success rates.

Recent research has shown that machine learning models are susceptible to adversarial examples, allowing attackers to trick a machine learning model into making a mistake and producing an incorrect output. Adversarial examples are commonly constructed or discovered by using gradient-based methods that require white-box access to the model. In most real-world AI system deployments, having complete access to the machine learning model is an unrealistic threat model. However, it is possible for an attacker to construct adversarial examples even in the black-box case - where we assume solely a query capability to the model - with a variety of approaches each with its advantages and shortcomings. We introduce AutoAttacker, a novel reinforcement learning framework where agents learn how to operate around the black-box model by querying it, to effectively extract the underlying decision behaviour, and to undermine it successfully. AutoAttacker is a first of kind framework that uses reinforcement learning and assumes nothing about the differentiability or structure of the underlying function and is thus robust towards common defenses like gradient obfuscation or adversarial training. Finally, without differentiable output, as in binary classification, most methods cease to operate and require either an approximation of the gradient, or another approach altogether. Our approach, however, maintains the capability to function when the output descriptiveness diminishes.

Deep machine learning techniques have shown promising results in network traffic classification, however, the robustness of these techniques under adversarial threats is still in question. Deep machine learning models are found vulnerable to small carefully crafted adversarial perturbations posing a major question on the performance of deep machine learning techniques. In this paper, we propose a black-box adversarial attack on network traffic classification. The proposed attack successfully evades deep machine learning-based classifiers which highlights the potential security threat of using deep machine learning techniques to realize autonomous networks.

Adversarial attacks have been the hot research field in artificial intelligence security. Decision-based black-box adversarial attacks are much more appropriate in the real-world scenarios, where only the final decisions of the targeted deep neural networks are accessible. However, since there is no available guidance for searching the imperceptive adversarial perturbation, boundary attack, one of the best performing decision-based black-box attacks, carries out computationally expensive search. For improving attack efficiency, we propose a novel black box explanation guided decision-based black-box adversarial attack. Firstly, the problem of decision-based adversarial attacks is modeled as a derivative-free and constraint optimization problem. To solve this optimization problem, the black box explanation guided constrained random search method is proposed to more quickly find the imperceptible adversarial example. The insights into the targeted deep neural networks explored by the black box explanation are fully used to accelerate the computationally expensive random search. Experimental results demonstrate that our proposed attack improves the attack efficiency by 64% compared with boundary attack.

The anonymity and decentralization of Bitcoin make it widely accepted in illegal transactions, such as money laundering, drug and weapon trafficking, gambling, to name a few, which has already caused significant security risk all around the world. The obvious de-anonymity approach that matches transaction addresses and users is not possible in practice due to limited annotated data set. In this paper, we divide addresses into four types, exchange, gambling, service, and general, and propose targeted addresses identification algorithms with high fault tolerance which may be employed in a wide range of applications. We use network representation learning to extract features and train imbalanced multi-classifiers. Experimental results validated the effectiveness of the proposed method.

Advances in technology have enabled tremendous progress in the development of a highly connected ecosystem of ubiquitous computing devices collectively called the Internet of Things (IoT). Ensuring the security of IoT devices is a high priority due to the sensitive nature of the collected data. Physically Unclonable Functions (PUFs) have emerged as critical hardware primitive for ensuring the security of IoT nodes. Malicious modeling of PUF architectures has proven to be difficult due to the inherently stochastic nature of PUF architectures. Extant approaches to malicious PUF modeling assume that a priori knowledge and physical access to the PUF architecture is available for malicious attack on the IoT node. However, many IoT networks make the underlying assumption that the PUF architecture is sufficiently tamper-proof, both physically and mathematically. In this work, we show that knowledge of the underlying PUF structure is not necessary to clone a PUF. We present a novel non-invasive, architecture independent, machine learning attack for strong PUF designs with a cloning accuracy of 93.5% and improvements of up to 48.31% over an alternative, two-stage brute force attack model. We also propose a machine-learning based countermeasure, discriminator, which can distinguish cloned PUF devices and authentic PUFs with an average accuracy of 96.01%. The proposed discriminator can be used for rapidly authenticating millions of IoT nodes remotely from the cloud server.

The concept of a decoy process is a new development of defensive deception beyond traditional honeypots. Decoy processes can be exceptionally effective in detecting malware, directly upon contact or by redirecting malware to decoy I/O. A key requirement is that they resemble their real counterparts very closely to withstand adversarial probes by threat actors. To be usable, decoy processes need to consume only a small fraction of the resources consumed by their real counterparts. Our contribution in this paper is twofold. We attack the resource utilization consistency of decoy processes provided by a neural network with a heatmap training mechanism, which we find to be insufficiently trained. We then devise machine learning over control flow graphs that improves the heatmap training mechanism. A neural network retrained by our work shows higher accuracy and defeats our attacks without a significant increase in its own resource utilization.

Severe class imbalance between the majority and minority classes in large datasets can prejudice Machine Learning classifiers toward the majority class. Our work uniquely consolidates two case studies, each utilizing three learners implemented within an Apache Spark framework, six sampling methods, and five sampling distribution ratios to analyze the effect of severe class imbalance on big data analytics. We use three performance metrics to evaluate this study: Area Under the Receiver Operating Characteristic Curve, Area Under the Precision-Recall Curve, and Geometric Mean. In the first case study, models were trained on one dataset (POST) and tested on another (SlowlorisBig). In the second case study, the training and testing dataset roles were switched. Our comparison of performance metrics shows that Area Under the Precision-Recall Curve and Geometric Mean are sensitive to changes in the sampling distribution ratio, whereas Area Under the Receiver Operating Characteristic Curve is relatively unaffected. In addition, we demonstrate that when comparing sampling methods, borderline-SMOTE2 outperforms the other methods in the first case study, and Random Undersampling is the top performer in the second case study.

With the exponential growth in the usage of electronic medical records (EMR), the amount of data generated by the healthcare industry has too increased exponentially. These large amounts of data, known as “Big Data” is mostly unstructured. Special big data analytics methods are required to process the information and retrieve information which is meaningful. As patient information in hospitals and other healthcare facilities become increasingly electronic, Big Data technologies are needed now more than ever to manage and understand this data. In addition, this information tends to be quite sensitive and needs a highly secure environment. However, current security algorithms are hard to be implemented because it would take a huge amount of time and resources. Security protocols in Big data are also not adequate in protecting sensitive information in the healthcare. As a result, the healthcare data is both heterogeneous and insecure. As a solution we propose the Secure Pattern-Based Data Sensitivity Framework (PBDSF), that uses machine learning mechanisms to identify the common set of attributes of patient data, data frequency, various patterns of codes used to identify specific conditions to secure sensitive information. The framework uses Hadoop and is built on Hadoop Distributed File System (HDFS) as a basis for our clusters of machines to process Big Data, and perform tasks such as identifying sensitive information in a huge amount of data and encrypting data that are identified to be sensitive.

Continuous and adaptive learning is an effective learning approach when dealing with highly dynamic and changing scenarios, where concept drift often happens. In a continuous, stream or adaptive learning setup, new measurements arrive continuously and there are no boundaries for learning, meaning that the learning model has to decide how and when to (re)learn from these new data constantly. We address the problem of adaptive and continual learning for network security, building dynamic models to detect network attacks in real network traffic. The combination of fast and big network measurements data with the re-training paradigm of adaptive learning imposes complex challenges in terms of data processing speed, which we tackle by relying on big data platforms for parallel stream processing. We build and benchmark different adaptive learning models on top of a novel big data analytics platform for network traffic monitoring and analysis tasks, and show that high speed-up computations (as high as × 6) can be achieved by parallelizing off-the-shelf stream learning approaches.

In the open network environment, the network offensive information is implanted in big data environment, so it is necessary to carry out accurate location marking of network offensive information, to realize network attack detection, and to implement the process of accurate location marking of network offensive information. Combined with big data analysis method, the location of network attack nodes is realized, but when network attacks cross in series, the performance of attack information tagging is not good. An accurate marking technique for network attack information is proposed based on big data fusion tracking recognition. The adaptive learning model combined with big data is used to mark and sample the network attack information, and the feature analysis model of attack information chain is designed by extracting the association rules. This paper classifies the data types of the network attack nodes, and improves the network attack detection ability by the task scheduling method of the network attack information nodes, and realizes the accurate marking of the network attacking information. Simulation results show that the proposed algorithm can effectively improve the accuracy of marking offensive information in open network environment, the efficiency of attack detection and the ability of intrusion prevention is improved, and it has good application value in the field of network security defense.

The task of attack attribution, i.e., identifying the entity responsible for an attack, is complicated and usually requires the involvement of an experienced security expert. Prior attempts to automate attack attribution apply various machine learning techniques on features extracted from the malware's code and behavior in order to identify other similar malware whose authors are known. However, the same malware can be reused by multiple actors, and the actor who performed an attack using a malware might differ from the malware's author. Moreover, information collected during an incident may contain many clues about the identity of the attacker in addition to the malware used. In this paper, we propose a method of attack attribution based on textual analysis of threat intelligence reports, using state of the art algorithms and models from the fields of machine learning and natural language processing (NLP). We have developed a new text representation algorithm which captures the context of the words and requires minimal feature engineering. Our approach relies on vector space representation of incident reports derived from a small collection of labeled reports and a large corpus of general security literature. Both datasets have been made available to the research community. Experimental results show that the proposed representation can attribute attacks more accurately than the baselines' representations. In addition, we show how the proposed approach can be used to identify novel previously unseen threat actors and identify similarities between known threat actors.

Intentionally deceptive content presented under the guise of legitimate journalism is a worldwide information accuracy and integrity problem that affects opinion forming, decision making, and voting patterns. Most so-called `fake news' is initially distributed over social media conduits like Facebook and Twitter and later finds its way onto mainstream media platforms such as traditional television and radio news. The fake news stories that are initially seeded over social media platforms share key linguistic characteristics such as making excessive use of unsubstantiated hyperbole and non-attributed quoted content. In this paper, the results of a fake news identification study that documents the performance of a fake news classifier are presented. The Textblob, Natural Language, and SciPy Toolkits were used to develop a novel fake news detector that uses quoted attribution in a Bayesian machine learning system as a key feature to estimate the likelihood that a news article is fake. The resultant process precision is 63.333% effective at assessing the likelihood that an article with quotes is fake. This process is called influence mining and this novel technique is presented as a method that can be used to enable fake news and even propaganda detection. In this paper, the research process, technical analysis, technical linguistics work, and classifier performance and results are presented. The paper concludes with a discussion of how the current system will evolve into an influence mining system.

This paper proposes a distributed deep learning framework for privacy-preserving medical data training. In order to avoid patients' data leakage in medical platforms, the hidden layers in the deep learning framework are separated and where the first layer is kept in platform and others layers are kept in a centralized server. Whereas keeping the original patients' data in local platforms maintain their privacy, utilizing the server for subsequent layers improves learning performance by using all data from each platform during training.

Nowadays, a massive number of data, referred as big data, are being collected from social networks and Internet of Things (IoT), which are of tremendous value. Many deep learning-based methods made great progress in the extraction of knowledge of those data. However, the knowledge extraction of the law data poses vast challenges on the deep learning, since the law data usually contain the privacy information. In addition, the amount of law data of an institution is not large enough to well train a deep model. To solve these challenges, some privacy-preserving deep learning are proposed to capture knowledge of privacy data. In this paper, we review the emerging topics of deep learning for the feature learning of the privacy data. Then, we discuss the problems and the future trend in deep learning for privacy-preserving feature learning on law data.

Frauds are known to be dynamic and have no patterns, hence they are not easy to identify. Fraudsters use recent technological advancements to their advantage. They somehow bypass security checks, leading to the loss of millions of dollars. Analyzing and detecting unusual activities using data mining techniques is one way of tracing fraudulent transactions. transactions. This paper aims to benchmark multiple machine learning methods such as k-nearest neighbor (KNN), random forest and support vector machines (SVM), while the deep learning methods such as autoencoders, convolutional neural networks (CNN), restricted boltzmann machine (RBM) and deep belief networks (DBN). The datasets which will be used are the European (EU) Australian and German dataset. The Area Under the ROC Curve (AUC), Matthews Correlation Coefficient (MCC) and Cost of failure are the 3-evaluation metrics that would be used.

In the existing situation, most of the business process are running through web applications. This helps the enterprises to grow their business efficiently which creates a good consumer relationship. But the main problem is that they failed to provide a vulnerable free environment. To overcome this issue in web applications, vulnerability assessment should be made periodically. They are many vulnerability assessment methodologies which occur earlier are not much proactive. So, machine learning is needed to provide a combined solution to determine vulnerability occurrence and percentage of vulnerability occurred in logical web pages. We use Decision Tree and Bayesian Belief Network (BBN) as a collective solution to find either vulnerability occur in web applications and the vulnerability occurred percentage on different logical web pages.

In this paper we propose a responsive autonomic and data-driven adaptive virtual networking framework (RAvN) that integrates the adaptive reconfigurable features of a popular SDN platform called open networking operating system (ONOS), the network performance statistics provided by traffic monitoring tools such as T-shark or sflow-RT and analytics and decision making skills provided from new and current machine learning techniques to detect and mitigate anomalous behavior. For this paper we focus on the development of novel detection schemes using a developed Centroid-based clustering technique and the Intragroup variance of data features within network traffic (C. Intra), with a multivariate gaussian distribution model fitted to the constant changes in the IP addresses of the network to accurately assist in the detection of low rate and high rate denial of service (DoS) attacks. We briefly discuss our ideas on the development of the decision-making and execution component using the concept of generating adaptive policy updates (i.e. anomalous mitigation solutions) on-the-fly to the ONOS SDN controller for updating network configurations and flows. In addition we provide the analysis on anomaly detection schemes used for detecting low rate and high rate DoS attacks versus a commonly used unsupervised machine learning technique Kmeans. The proposed schemes outperformed Kmeans significantly. The multivariate clustering method and the intragroup variance recorded 80.54% and 96.13% accuracy respectively while Kmeans recorded 72.38% accuracy.

Devices that are connected to the Internet are very interesting to security researchers as are at high risk of being attacked, compromised or otherwise abused. To investigate the root causes of the risks it is necessary to understand what classes of devices are affected in different ways. These devices are heterogeneous, thus making it impractical to classify large sets by applying static rules. We propose improvements for manually labelling training sets using HTTP response features for future classification using a neural network.

Despite their popularity, Security Operation Centers (SOCs) are facing increasing challenges and pressure due to the growing volume, velocity and variety of the IT infrastructure and security data observed on a daily basis. Due to the mixed performance of current technological solutions, e.g. IDS and SIEM, there is an over-reliance on manual analysis of the events by human security analysts. This creates huge backlogs and slow down considerably the resolution of critical security events. Obvious solutions include increasing accuracy and efficiency in the automation of crucial aspects of the SOC workflow, such as the event classification and prioritization. In the current paper, we present a new approach for SOC event classification by identifying a set of new features using graphical analysis and classifying using a deep neural network model. Experimental evaluation using real SOC event log data yields very encouraging results in terms of classification accuracy.

Emerging hardware architectures for Deep Neural Networks (DNNs) are being commercialized and considered as the hardware- level Intellectual Property (IP) of the device providers. However, these intelligent devices might be abused and such vulnerability has not been identified. The unregulated usage of intelligent platforms and the lack of hardware-bounded IP protection impair the commercial advantage of the device provider and prohibit reliable technology transfer. Our goal is to design a systematic methodology that provides hardware-level IP protection and usage control for DNN applications on various platforms. To address the IP concern, we present DeepAttest, the first on-device DNN attestation method that certifies the legitimacy of the DNN program mapped to the device. DeepAttest works by designing a device-specific fingerprint which is encoded in the weights of the DNN deployed on the target platform. The embedded fingerprint (FP) is later extracted with the support of the Trusted Execution Environment (TEE). The existence of the pre-defined FP is used as the attestation criterion to determine whether the queried DNN is authenticated. Our attestation framework ensures that only authorized DNN programs yield the matching FP and are allowed for inference on the target device. DeepAttest provisions the device provider with a practical solution to limit the application usage of her manufactured hardware and prevents unauthorized or tampered DNNs from execution. We take an Algorithm/Software/Hardware co-design approach to optimize DeepAttest's overhead in terms of latency and energy consumption. To facilitate the deployment, we provide a high-level API of DeepAttest that can be seamlessly integrated into existing deep learning frameworks and TEEs for hardware-level IP protection and usage control. Extensive experiments corroborate the fidelity, reliability, security, and efficiency of DeepAttest on various DNN benchmarks and TEE-supported platforms.

The use of the Internet of Things (IoT) devices has surged in recent years. However, due to the lack of substantial security, IoT devices are vulnerable to cyber-attacks like Denial-of-Service (DoS) attacks. Most of the current security solutions are either computationally expensive or unscalable as they require known attack signatures or full packet inspection. In this paper, we introduce a novel Graph-based Outlier Detection in Internet of Things (GODIT) approach that (i) represents smart home IoT traffic as a real-time graph stream, (ii) efficiently processes graph data, and (iii) detects DoS attack in real-time. The experimental results on real-world data collected from IoT-equipped smart home show that GODIT is more effective than the traditional machine learning approaches, and is able to outperform current graph-stream anomaly detection approaches.