Biblio

This paper introduces DeepCheck, a new approach for validating Deep Neural Networks (DNNs) based on core ideas from program analysis, specifically from symbolic execution. DeepCheck implements techniques for lightweight symbolic analysis of DNNs and applies them in the context of image classification to address two challenging problems: 1) identification of important pixels (for attribution and adversarial generation); and 2) creation of adversarial attacks. Experimental results using the MNIST data-set show that DeepCheck's lightweight symbolic analysis provides a valuable tool for DNN validation.

The world is witnessing an exceptional expansion in the cloud enabled services which is further growing day by day due to advancement & requirement of technology. However, the identification of vulnerabilities & its exploitation in the cloud computing will always be the major challenge and concern for any cloud computing system. To understand the challenges and its consequences and further provide mitigation techniques for the vulnerabilities, the identification of cloud specific vulnerabilities needs to be examined first and after identification of vulnerabilities a detailed taxonomy must be positioned. In this paper several cloud specific identified vulnerabilities have been studied which is listed by the NVD, ENISA CSA etc accordingly a unified taxonomy for security vulnerabilities has been prepared. In this paper we proposed a comprehensive taxonomy for cloud specific vulnerabilities on the basis of several parameters like attack vector, CVSS score, complexity etc which will be further act as input for the analysis and mitigation of cloud vulnerabilities. Scheming of Taxonomy of vulnerabilities is an effective way for cloud administrators, cloud mangers, cloud consumers and other stakeholders for identifying, understanding and addressing security risks.

The Joint Test Action Group (JTAG) standards define test and debug architectures that are ingrained within much of today's commercial silicon. In particular, the IEEE Std. 1149.1 (Standard Test Access Port and Boundary Scan Architecture) forms the foundation of on-chip embedded instrumentation that is used extensively for everything from prototype board bring-up to firmware triage to field and depot system repair. More recently, JTAG is being used in-system as a hardware/firmware mechanism for Built-In Test (BIT), addressing No Fault Found (NFF) and materiel availability issues. Its power and efficacy are a direct outcome of being a ubiquitously available, embedded on-die instrument that is inherent in most electronic devices. While JTAG is indispensable for all aspects of test and debug, it suffers from a lack of inherent security. Unprotected, it can represent a security weakness, exposing a back-door vulnerability through which hackers can reverse engineer, extract sensitive data from, or disrupt systems. More explicitly, JTAG can be used to: - Read and write from system memory - Pause execution of firmware (by setting breakpoints) - Patch instructions or data in memory - Inject instructions directly into the pipeline of a target chip (without modifying memory) - Extract firmware (for reverse engineering/vulnerability research) - Execute private instructions to activate other engines within the chip As a low-level means of access to a powerful set of capabilities, the JTAG interface must be safeguarded against unauthorized intrusions and attacks. One method used to protect platforms against such attacks is to physically fuse off the JTAG Test Access Ports, either at the integrated circuit or the board level. But, given JTAG's utility, alternative approaches that allow for both security and debug have become available, especially if there is a hardware root of trust on the platform. These options include chip lock and key registers, challenge-response mechanisms, secure key systems, TDI/TDO encryption, and other authentication/authorization techniques. This paper reviews the options for safe access to JTAG-based debug and test embedded instrumentation.

This paper mainly focuses on presenting a novel attack detection system to thread out the risk issues in IoT. The presented attack detection system links the interconnection of DevOps as it creates the correlation between development and IT operations. Further, the presented attack detection model ensures the operational security of different applications. In view of this, the implemented system incorporates two main stages named Proposed Feature Extraction process and Classification. The data from every application is processed with the initial stage of feature extraction, which concatenates the statistical and higher-order statistical features. After that, these extracted features are supplied to classification process, where determines the presence of attacks. For this classification purpose, this paper aims to deploy the optimized Deep Belief Network (DBN), where the activation function is tuned optimally. Furthermore, the optimal tuning is done by a renowned meta-heuristic algorithm called Lion Algorithm (LA). Finally, the performance of proposed work is compared and proved over other conventional methods.

Power system intelligent terminal equipment is widely used in real-time monitoring, data acquisition, power management, power distribution and other tasks of smart grid. The power system intelligent terminal can obtain various information of users and power companies in the power grid, but there is still a lack of protection means for the connection and communication process of the terminal components. In this paper, a novel method based on improved deep belief network(IDBN) is proposed to accomplish the business-level security monitoring and attack detection of power system terminal. A non-intrusive business-level monitoring platform for power system terminals is established, which uses energy metering intelligent terminals as an example for non-intrusive data collection. Based on this platform, the I-DBN extracts the spatial and temporal attack characteristics of the external monitoring data of the system. Some fault conditions and cyber attacks of the model have been simulated to demonstrate the effectiveness of the proposed detection method and the results show excellent performance. The method and platform proposed in this paper can be extended to other services in the power industry, providing a theoretical basis and implementation method for realizing the security monitoring of power system intelligent terminals from the business level.

OpenFlow has been the main standard protocol of software defined networking (SDN) since the launch of this new networking paradigm. It is a programmable network protocol that controls traffic flows among switches and routers regardless of their platforms. Its security relies on the optional implementation of Transport Layer Security (TLS) which has been proven vulnerable. The aim of this research was to develop a secured OpenFlow, so-called Secured-OF. A stateful firewall was used to store state information for further analysis. Dynamic Bayesian Network (DBN) was used to learn denial-of-service attack and distributed denial-of-service attack. It analyzes packet states to determine the nature of an attack and adds that piece of information to the flow table entry. The proposed Secured-OF model in Ryu controller was evaluated with several performance metrics. The analytical evaluation of the proposed Secured-OF scheme was performed on an emulated network. The results showed that the proposed Secured-OF scheme offers a high attack detection accuracy at 99.5%. In conclusion, it was able to improve the security of the OpenFlow controller dramatically with trivial performance degradation compared to an SDN with no security implementation.

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.

Manufacturing enterprises are constantly exploring new ways to improve their own production processes to address the increasing demand of customized production. However, such enterprises show a low degree of flexibility, which mainly results from the need to configure new production equipment at design and run time. In this paper we propose self-adaptation as an approach to improve data transmission flexibility in Industry 4.0 environments. We implement an autonomic manager using a generic autonomic management framework, which applies the most appropriate data transmission configuration based on security and business process related requirements, such as performance. The experimental evaluation is carried out in a MQTT infrastructure and the results show that using self-adaptation can significantly improve the trade-off between security and performance. We then propose to integrate anomaly detection methods as a solution to support self-adaptation by monitoring and learning the normal behavior of an industrial system and show how this can be used by the generic autonomic management framework.

Autonomic resource management for distributed edge computing systems provides an effective means of enabling dynamic placement and adaptation in the face of network changes, load dynamics, and failures. However, adaptation in-and-of-itself offers a side channel by which malicious entities can extract valuable information. An attacker can take advantage of autonomic resource management techniques to fool a system into misallocating resources and crippling applications. Using a few scenarios, we outline how attacks can be launched using partial knowledge of the resource management substrate - with as little as a single compromised node. We argue that any system that provides adaptation must consider resource management as an attack surface. As such, we propose ADAPT2, a framework that incorporates concepts taken from Moving-Target Defense and state estimation techniques to ensure correctness and obfuscate resource management, thereby protecting valuable system and application information from leaking.

Point of Sale (POS) systems has become the technology of choice for most businesses and offering number of advantages over traditional cash registers. They manage staffs, customers, transaction, inventory, sale and labor reporting, price adjustment, as well as keeping track of cash flow, expense management, reducing human errors and more. Whether traditional on-premise POS, or Cloud-Bases POS, they help businesses to run more efficiently. However, despite all these advantages, POS systems are becoming targets of a number of cyber-attacks. Security of a POS system is a key requirement of the Payment Card Industry Data Security Standard (PCI DSS). This paper undertakes research into the PCI DSS and its accompanying standards, in an attempt to break or bypass security measures using varying degrees of vulnerability and penetration attacks in a methodological format. The resounding goal of this experimentation is to achieve a basis from which attacks can be made against a realistic networking environment from whence an intruder can bypass security measures thus exposing a vulnerability in the PCI DSS and potentially exposing confidential customer payment information.

We present a system architecture for autonomic operation, administration and maintenance of both the optical and digital layers within the integrated optical transport network infrastructure. This framework encompasses the end-to-end instrumentation: From equipment commissioning to automatic discovery and bring-up, to self-managed, self-(re)configuring optical transport layer. We leverage prevalent networking protocols to build an autonomic control plane for the optical network elements. Various aspects of security, a critical element for self-managed operations, are addressed. We conclude with a discussion on the interaction with SDN, and how autonomic functions can benefit from these capabilities, a brief survey of standardization activities and scope for future work.

Cyber-attacks against cloud storage infrastructure e.g. Amazon S3 and Google Cloud Storage, have increased in recent years. One reason for this development is the rising adoption of cloud storage for various purposes. Robust counter-measures are therefore required to tackle these attacks especially as traditional techniques are not appropriate for the evolving attacks. We propose a two-pronged approach to address these challenges in this paper. The first approach involves dynamic snapshotting and recovery strategies to detect and partially neutralize security events. The second approach builds on the initial step by automatically correlating the generated alerts with cloud event log, to extract actionable intelligence for incident response. Thus, malicious activities are investigated, identified and eliminated. This approach is implemented in SlingShot, a cloud threat detection and incident response system which extends our earlier work - CSBAuditor, which implements the first step. The proposed techniques work together in near real time to mitigate the aforementioned security issues on Amazon Web Services (AWS) and Google Cloud Platform (GCP). We evaluated our techniques using real cloud attacks implemented with static and dynamic methods. The average Mean Time to Detect is 30 seconds for both providers, while the Mean Time to Respond is 25 minutes and 90 minutes for AWS and GCP respectively. Thus, our proposal effectively tackles contemporary cloud attacks.

The Internet of Things (IoT) relies on sensor devices to measure real-world phenomena in order to provide IoT services. The sensor readings are shared with multiple entities, such as IoT services, other IoT devices or other third parties. The collected data may be sensitive and include personal information. To protect the privacy of the users, the data needs to be protected through an encryption algorithm. For sharing cryptographic cipher-texts with a group of users Attribute-Based Encryption (ABE) is well suited, as it does not require to create group keys. However, the creation of ABE cipher-texts is slow when executed on resource constraint devices, such as IoT sensors. In this paper, we present a modification of an ABE scheme, which not only allows to encrypt data efficiently using ABE but also reduces the size of the cipher-text, that must be transmitted by the sensor. We also show how our modification can be used to realise an instantaneous key revocation mechanism.

Motivated by the complexity of cryptographic proofs, we propose methods to automate the construction and verification of cryptographic proofs in the standard model. Proofs in the standard model (as opposed to the random oracle model) are the gold standard of cryptographic proofs, and most cryptographic protocols strive to achieve them. The burgeoning complexity of cryptographic proofs implies that such proofs are prone to errors, and are hard to write, much less verify. In this paper, we propose techniques to generate automated proofs for attribute-based encryption schemes in the standard model, building upon a prototype tool, AutoG&P due to Barthe et al. In doing so, we significantly expand the scope of AutoG&P to support a rich set of data types such as multi-dimensional arrays, and constructs commonly used in cryptographic protocols such as monotone-access structures, and linear secret-sharing schemes. We also provide support for a extended class of pairing-based assumptions. We demonstrate the usefulness of our extensions by giving automated proofs of the Lewko et al. attribute-based encryption scheme, and the Waters' ciphertext-policy attribute-based encryption scheme.

Networks of and embedded (IoT) devices are becoming increasingly popular, particularly, in settings such as smart homes, factories and vehicles. These networks can include numerous (potentially diverse) devices that collectively perform certain tasks. In order to guarantee overall safety and privacy, especially in the face of remote exploits, software integrity of each device must be continuously assured. This can be achieved by Remote Attestation (RA) - a security service for reporting current software state of a remote and untrusted device. While RA of a single device is well understood, collective RA of large numbers of networked embedded devices poses new research challenges. In particular, unlike single-device RA, collective RA has not benefited from any systematic treatment. Thus, unsurprisingly, prior collective RA schemes are designed in an ad hoc fashion. Our work takes the first step toward systematic design of collective RA, in order to help place collective RA onto a solid ground and serve as a set of design guidelines for both researchers and practitioners. We explore the design space for collective RA and show how the notions of security and effectiveness can be formally defined according to a given application domain. We then present and evaluate a concrete collective RA scheme systematically designed to satisfy these goals.

Network communication data are high-dimensional and spatiotemporal, and their information content is often degraded by common traffic analysis methods. For long-term network attack detection based on network flows, it is important to extract a discriminative, high-dimensional intrinsic representation of such flows. This work focuses on a hybrid deep neural network design using a combination of a convolutional neural network (CNN) and long short-term memory (LSTM) with graph similarity measures to learn high-dimensional representations from the network traffic. In particular, examining a set of network flows, we commence by constructing a temporal communication graph and then computing graph kernel matrices. Having obtained the kernel matrices, for each graph, we use the kernel value between graphs and calculate graph characterization vectors by graph signal processing. This vector can be regarded as a kernel-based similarity embedding vector of the graph that integrates structural similarity information and leverages efficient graph kernel using the graph Laplacian matrix. Our approach exploits graph structures as the additional prior information, the graph Laplacian matrix for feature extraction and hybrid deep learning models for long-term information learning on communication graphs. Experiments on two real-world network attack datasets show that our approach can extract more discriminative representations, leading to an improved accuracy in a supervised classification task. The experimental results show that our method increases the overall accuracy by approximately 10%-15%.

Organizations perform security analysis for assessing network health and safe-guarding their growing networks through Vulnerability Assessments (AKA VA Scans). The output of VA scans is reports on individual hosts and its vulnerabilities, which, are of little use as the origin of the attack can't be located from these. Attack Graphs, generated without an in-depth analysis of the VA reports, are used to fill in these gaps, but only provide cursory information. This study presents an effective model of depicting the devices and the data flow that efficiently identifies the weakest nodes along with the concerned vulnerability's origin.The complexity of the attach graph using MulVal has been greatly reduced using the proposed approach of using the risk and CVSS base score as evaluation criteria. This makes it easier for the user to interpret the attack graphs and thus reduce the time taken needed to identify the attack paths and where the attack originates from.

In this paper, we propose a game-attack graph-based risk assessment model for industrial Internet system. Firstly, use non-destructive asset profiling to scan components and devices included in the system and their open services and communication protocols. Further compare the CNVD and CVE to find the vulnerability through the search engine keyword segment matching method, and generate an asset threat list. Secondly, build the attack rule base based on the network information, and model the system using the attribute attack graph. Thirdly, combine the game theory with the idea of the established model. Finally, optimize and quantify the analysis to get the best attack path and the best defense strategy.

The lack of knowledge about API correct usage rules is one of the main reasons that APIs are employed incorrectly by programmers, which in some cases lead to serious security vulnerabilities. However, finding a correct usage rule for an API is a time-consuming and error-prone task, particularly in the absence of an API documentation. Existing approaches to extract correct usage rules are mostly based on majority API usages, assuming the correct usage is prevalent. Although statistically extracting API correct usage rules achieves reasonable accuracy, it cannot work correctly in the absence of a fair amount of sample usages. We propose inferring API correct usage rules independent of the number of sample usages by leveraging an API tree structure. In an API tree, each node is an API, and each node's children are APIs called by the parent API. Starting from lower-level APIs, it is possible to infer the correct usage rules for them by utilizing the available correct usage rules of their children. We developed a tool based on our idea for inferring API correct usages rules hierarchically, and have applied it to the source code of Linux kernel v4.3 drivers and found 24 previously reported bugs.

Security is often a critical problem in software systems. The consequences of the failure lead to substantial economic loss or extensive environmental damage. Developing secure software is challenging, and retrofitting existing systems to introduce security is even harder. In this paper, we propose an automated approach for Finding and Repairing Bugs based on security patterns (FireBugs), to repair defects causing security vulnerabilities. To locate and fix security bugs, we apply security patterns that are reusable solutions comprising large amounts of software design experience in many different situations. In the evaluation, we investigated 2,800 Android app repositories to apply our approach to 200 subject projects that use javax.crypto APIs. The vision of our automated approach is to reduce software maintenance burdens where the number of outstanding software defects exceeds available resources. Our ultimate vision is to design more security patterns that have a positive impact on software quality by disseminating correlated sets of best security design practices and knowledge.

With the advancements in enterprise-level business development, the demand for new applications and services is overwhelming. For the development and delivery of such applications and services, enterprise businesses rely on Application Programming Interfaces (APIs). API management and classification is a cumbersome task considering the rapid increase in the number of APIs, and API to API calls. API Mashups, domain APIs and API service mesh are a few recommended techniques for ease of API creation, management, and monitoring. API service mesh is considered as one of the techniques in this regard, in which the service plane and the control plane are separated for improving efficiency as well as security. In this paper, we propose and implement a security framework for the creation of a secure API service mesh using Istio and Kubernetes. Afterwards, we propose an smart association model for automatic association of new APIs to already existing categories of service mesh. To the best of our knowledge, this smart association model is the first of its kind.

Expected and unexpected risks in cloud computing, which included data security, data segregation, and the lack of control and knowledge, have led to some dilemmas in several fields. Among all of these dilemmas, the privacy problem is even more paramount, which has largely constrained the prevalence and development of cloud computing. There are several privacy protection algorithms proposed nowadays, which generally include two categories, Anonymity algorithm, and differential privacy mechanism. Since many types of research have already focused on the efficiency of the algorithms, few of them emphasized the different orientation and demerits between the two algorithms. Motivated by this emerging research challenge, we have conducted a comprehensive survey on the two popular privacy protection algorithms, namely K-Anonymity Algorithm and Differential Privacy Algorithm. Based on their principles, implementations, and algorithm orientations, we have done the evaluations of these two algorithms. Several expectations and comparisons are also conducted based on the current cloud computing privacy environment and its future requirements.

Anonymity platforms route the traffic over a network of special routers that are known as mixes and implement various traffic disruption techniques to hide the communicating users' identities. Batch mixes in particular anonymize communicating peers by allowing message exchange to take place only after a sufficient number of messages (a batch) accumulate, thus introducing delay. We introduce a queueing model for batch mix and study its delay properties. Our analysis shows that delay of a batch mix grows quickly as the batch size gets close to the number of senders connected to the mix. We then propose a randomized batch mixing strategy and show that it achieves much better delay scaling in terms of the batch size. However, randomization is shown to reduce the anonymity preserving capabilities of the mix. We also observe that queueing models are particularly useful to study anonymity metrics that are more practically relevant such as the time-to-deanonymize metric.

In the privacy protection method based on user collaboration, all participants and collaborators must share the maximum anonymity value set in the anonymous group. No user can get better quality of service by reducing the anonymity requirement. In this paper, a privacy protection algorithm random-QBE, which divides query information into blocks and exchanges randomly, is proposed. Through this method, personalized anonymity, query diversity and location anonymity in user cooperative privacy protection can be realized. And through multi-hop communication between collaborative users, this method can also satisfy the randomness of anonymous location, so that the location of the applicant is no longer located in the center of the anonymous group, which further increases the ability of privacy protection. Experiments show that the algorithm can complete the processing in a relatively short time and is suitable for deployment in real environment to protect user's location privacy.

Social networks are highly preferred to express opinions, share information, and communicate with others on arbitrary topics. However, the downside is that many cybercriminals are leveraging social networks for cyber-crime. Internet Relay Chat (IRC) is the important social networks which can grant the anonymity to users by allowing them to connect channels without sign-up process. Therefore, IRC has been the playground of hackers and anonymous users for various operations such as hacking, cracking, and carding. Hence, it is urgent to study effective methods which can identify the authors behind the IRC messages. In this paper, we design an autonomic IRC monitoring system, performing recursive deep learning for classifying threat levels of messages and develop a novel author verification approach with one-class classification with deep autoencoder neural networks. The experimental results show that our approach can successfully perform effective author verification for IRC users.