Biblio
With the evolution of network threat, identifying threat from internal is getting more and more difficult. To detect malicious insiders, we move forward a step and propose a novel attribute classification insider threat detection method based on long short term memory recurrent neural networks (LSTM-RNNs). To achieve high detection rate, event aggregator, feature extractor, several attribute classifiers and anomaly calculator are seamlessly integrated into an end-to-end detection framework. Using the CERT insider threat dataset v6.2 and threat detection recall as our performance metric, experimental results validate that the proposed threat detection method greatly outperforms k-Nearest Neighbor, Isolation Forest, Support Vector Machine and Principal Component Analysis based threat detection methods.
In big data environments with big number of users and high volume of data, we need to manage the corresponding huge number of security policies. Due to the distributed management of these policies, they may contain several anomalies, such as conflicts and redundancies, which may lead to both safety and availability problems. The distributed systems guided by such security policies produce a huge number of access logs. Due to potential security breaches, the access logs may show the presence of non-allowed accesses. This may also be a consequence of conflicting rules in the security policies. In this paper, we present an ongoing work on developing an environment for verifying and correcting security policies. To make the approach efficient, an access log is used as input to determine suspicious parts of the policy that should be considered. The approach is also made efficient by clustering the policy and the access log and considering separately the obtained clusters. The clustering technique and the use of access log significantly reduces the complexity of the suggested approach, making it scalable for large amounts of data.
Massive and dynamic networks arise in many practical applications such as social media, security and public health. Given an evolutionary network, it is crucial to detect structural anomalies, such as vertices and edges whose "behaviors'' deviate from underlying majority of the network, in a real-time fashion. Recently, network embedding has proven a powerful tool in learning the low-dimensional representations of vertices in networks that can capture and preserve the network structure. However, most existing network embedding approaches are designed for static networks, and thus may not be perfectly suited for a dynamic environment in which the network representation has to be constantly updated. In this paper, we propose a novel approach, NetWalk, for anomaly detection in dynamic networks by learning network representations which can be updated dynamically as the network evolves. We first encode the vertices of the dynamic network to vector representations by clique embedding, which jointly minimizes the pairwise distance of vertex representations of each walk derived from the dynamic networks, and the deep autoencoder reconstruction error serving as a global regularization. The vector representations can be computed with constant space requirements using reservoir sampling. On the basis of the learned low-dimensional vertex representations, a clustering-based technique is employed to incrementally and dynamically detect network anomalies. Compared with existing approaches, NetWalk has several advantages: 1) the network embedding can be updated dynamically, 2) streaming network nodes and edges can be encoded efficiently with constant memory space usage, 3) flexible to be applied on different types of networks, and 4) network anomalies can be detected in real-time. Extensive experiments on four real datasets demonstrate the effectiveness of NetWalk.
Supervisory Control and Data Acquisition (SCADA) systems play a critical role in the operation of large-scale distributed industrial systems. There are many vulnerabilities in SCADA systems and inadvertent events or malicious attacks from outside as well as inside could lead to catastrophic consequences. Network-based intrusion detection is a preferred approach to provide security analysis for SCADA systems due to its less intrusive nature. Data in SCADA network traffic can be generally divided into transport, operation, and content levels. Most existing solutions only focus on monitoring and event detection of one or two levels of data, which is not enough to detect and reason about attacks in all three levels. In this paper, we develop a novel edge-based multi-level anomaly detection framework for SCADA networks named EDMAND. EDMAND monitors all three levels of network traffic data and applies appropriate anomaly detection methods based on the distinct characteristics of data. Alerts are generated, aggregated, prioritized before sent back to control centers. A prototype of the framework is built to evaluate the detection ability and time overhead of it.
The paper offers an approach for implementation of intelligent agents intended for network traffic and security risk analysis in cyber-physical systems. The agents are based on the algorithm of pseudo-gradient adaptive anomaly detection and fuzzy logical inference. The suggested algorithm operates in real time. The fuzzy logical inference is used for regulation of algorithm parameters. The variants of the implementation are proposed. The experimental assessment of the approach confirms its high speed and adequate accuracy for network traffic analysis.
Nowadays, most of the world's population has become much dependent on computers for banking, healthcare, shopping, and telecommunication. Security has now become a basic norm for computers and its resources since it has become inherently insecure. Security issues like Denial of Service attacks, TCP SYN Flooding attacks, Packet Dropping attacks and Distributed Denial of Service attacks are some of the methods by which unauthorized users make the resource unavailable to authorized users. There are several security mechanisms like Intrusion Detection System, Anomaly detection and Trust model by which we can be able to identify and counter the abuse of computer resources by unauthorized users. This paper presents a survey of several security mechanisms which have been implemented using Fuzzy logic. Fuzzy logic is one of the rapidly developing technologies, which is used in a sophisticated control system. Fuzzy logic deals with the degree of truth rather than the Boolean logic, which carries the values of either true or false. So instead of providing only two values, we will be able to define intermediate values.
Rapid development of internet and network technologies has led to considerable increase in number of attacks. Intrusion detection system is one of the important ways to achieve high security in computer networks. However, it have curse of dimensionality which tends to increase time complexity and decrease resource utilization. To improve the ability of detecting anomaly intrusions, a combined algorithm is proposed based on Weighted Fuzzy C-Mean Clustering Algorithm (WFCM) and Fuzzy logic. Decision making is performed in two stages. In the first stage, WFCM algorithm is applied to reduce the input data space. The reduced dataset is then fed to Fuzzy Logic scheme to build the fuzzy sets, membership function and the rules that decide whether an instance represents an anomaly or not.
Malicious traffic has garnered more attention in recent years, owing to the rapid growth of information technology in today's world. In 2007 alone, an estimated loss of 13 billion dollars was made from malware attacks. Malware data in today's context is massive. To understand such information using primitive methods would be a tedious task. In this publication we demonstrate some of the most advanced deep learning techniques available, multilayer perceptron (MLP) and J48 (also known as C4.5 or ID3) on our selected dataset, Advanced Security Network Metrics & Non-Payload-Based Obfuscations (ASNM-NPBO) to show that the answer to managing cyber security threats lie in the fore-mentioned methodologies.
Machine-to-Machine (M2M) networks being connected to the internet at large, inherit all the cyber-vulnerabilities of the standard Information Technology (IT) systems. Since perfect cyber-security and robustness is an idealistic construct, it is worthwhile to design intrusion detection schemes to quickly detect and mitigate the harmful consequences of cyber-attacks. Volumetric anomaly detection have been popularized due to their low-complexity, but they cannot detect low-volume sophisticated attacks and also suffer from high false-alarm rate. To overcome these limitations, feature-based detection schemes have been studied for IT networks. However these schemes cannot be easily adapted to M2M systems due to the fundamental architectural and functional differences between the M2M and IT systems. In this paper, we propose novel feature-based detection schemes for a general M2M uplink to detect Distributed Denial-of-Service (DDoS) attacks, emergency scenarios and terminal device failures. The detection for DDoS attack and emergency scenarios involves building up a database of legitimate M2M connections during a training phase and then flagging the new M2M connections as anomalies during the evaluation phase. To distinguish between DDoS attack and emergency scenarios that yield similar signatures for anomaly detection schemes, we propose a modified Canberra distance metric. It basically measures the similarity or differences in the characteristics of inter-arrival time epochs for any two anomalous streams. We detect device failures by inspecting for the decrease in active M2M connections over a reasonably large time interval. Lastly using Monte-Carlo simulations, we show that the proposed anomaly detection schemes have high detection performance and low-false alarm rate.
Compromised smart meters sending false power consumption data in Advanced Metering Infrastructure (AMI) may have drastic consequences on the smart grid»s operation. Most existing defense models only deal with electricity theft from individual customers (isolated attacks) using supervised classification techniques that do not offer scalable or real time solutions. Furthermore, the cyber and interconnected nature of AMIs can also be exploited by organized adversaries who have the ability to orchestrate simultaneous data falsification attacks after compromising several meters, and also have more complex goals than just electricity theft. In this paper, we first propose a real time semi-supervised anomaly based consensus correction technique that detects the presence and type of smart meter data falsification, and then performs a consensus correction accordingly. Subsequently, we propose a semi-supervised consensus based trust scoring model, that is able to identify the smart meters injecting false data. The main contribution of the proposed approach is to provide a practical framework for compromised smart meter identification that (i) is not supervised (ii) enables quick identification (iii) scales classification error rates better for larger sized AMIs; (iv) counters threats from both isolated and orchestrated attacks; and (v) simultaneously works for a variety of data falsification types. Extensive experimental validation using two real datasets from USA and Ireland, demonstrates the ability of our proposed method to identify compromised meters in near real time across different datasets.
Smart grids require communication networks for supervision functions and control operations. With this they become attractive targets for attackers. In newer power grids, State Estimation (SE) is often performed based on Kalman Filters (KFs) to deal with noisy measurement data and detect Bad Data (BD) due to failures in the measurement system. Nevertheless, in a setting where attackers can gain access to modify sensor data, they can exploit the fact that SE is used to process the data. In this paper, we show how an attacker can modify Phasor Measurement Unit (PMU) sensor data in a way that it remains undetected in the state estimation process. We show how anomaly detection methods based on innovation gain fail if an attacker is aware of the state estimation and uses the right strategy to circumvent detection.
Intrusion detection systems define an important and dynamic research area for cybersecurity. The role of Intrusion Detection System within security architecture is to improve a security level by identification of all malicious and also suspicious events that could be observed in computer or network system. One of the more specific research areas related to intrusion detection is anomaly detection. Anomaly-based intrusion detection in networks refers to the problem of finding untypical events in the observed network traffic that do not conform to the expected normal patterns. It is assumed that everything that is untypical/anomalous could be dangerous and related to some security events. To detect anomalies many security systems implements a classification or clustering algorithms. However, recent research proved that machine learning models might misclassify adversarial events, e.g. observations which were created by applying intentionally non-random perturbations to the dataset. Such weakness could increase of false negative rate which implies undetected attacks. This fact can lead to one of the most dangerous vulnerabilities of intrusion detection systems. The goal of the research performed was verification of the anomaly detection systems ability to resist this type of attack. This paper presents the preliminary results of tests taken to investigate existence of attack vector, which can use adversarial examples to conceal a real attack from being detected by intrusion detection systems.
Attackers create new threats and constantly change their behavior to mislead security systems. In this paper, we propose an adaptive threat detection architecture that trains its detection models in real time. The major contributions of the proposed architecture are: i) gather data about zero-day attacks and attacker behavior using honeypots in the network; ii) process data in real time and achieve high processing throughput through detection schemes implemented with stream processing technology; iii) use of two real datasets to evaluate our detection schemes, the first from a major network operator in Brazil and the other created in our lab; iv) design and development of adaptive detection schemes including both online trained supervised classification schemes that update their parameters in real time and learn zero-day threats from the honeypots, and online trained unsupervised anomaly detection schemes that model legitimate user behavior and adapt to changes. The performance evaluation results show that proposed architecture maintains an excellent trade-off between threat detection and false positive rates and achieves high classification accuracy of more than 90%, even with legitimate behavior changes and zero-day threats.
Return-Oriented Programming (ROP) has emerged as one of the most widely used techniques to exploit software vulnerabilities. Unfortunately, existing ROP protections suffer from a number of shortcomings: they require access to source code and compiler support, focus on specific types of gadgets, depend on accurate disassembly and construction of Control Flow Graphs, or use hardware-dependent (microarchitectural) characteristics. In this paper, we propose EigenROP, a novel system to detect ROP payloads based on unsupervised statistical learning of program characteristics. We study, for the first time, the feasibility and effectiveness of using microarchitecture-independent program characteristics – namely, memory locality, register traffic, and memory reuse distance – for detecting ROP. We propose a novel directional statistics based algorithm to identify deviations from the expected program characteristics during execution. EigenROP works transparently to the protected program, without requiring debug information, source code or disassembly. We implemented a dynamic instrumentation prototype of EigenROP using Intel Pin and measured it against in-the-wild ROP exploits and on payloads generated by the ROP compiler ROPC. Overall, EigenROP achieved significantly higher accuracy than prior anomaly-based solutions. It detected the execution of the ROP gadget chains with 81% accuracy, 80% true positive rate, only 0.8% false positive rate, and incurred comparable overhead to similar Pin-based solutions. This article is summarized in: the morning paper an interesting/influential/important paper from the world of CS every weekday morning, as selected by Adrian Colyer
Many network intrusion detection systems use byte sequences to detect lateral movements that exploit remote vulnerabilities. Attackers bypass such detection by stealing valid credentials and using them to transmit from one computer to another without creating abnormal network traffic. We call this method Credential-based Lateral Movement. To detect this type of lateral movement, we develop the concept of a Network Login Structure that specifies normal logins within a given network. Our method models a network login structure by automatically extracting a collection of login patterns by using a variation of the market-basket algorithm. We then employ an anomaly detection approach to detect malicious logins that are inconsistent with the enterprise network's login structure. Evaluations show that the proposed method is able to detect malicious logins in a real setting. In a simulated attack, our system was able to detect 82% of malicious logins, with a 0.3% false positive rate. We used a real dataset of millions of logins over the course of five months within a global financial company for evaluation of this work.
We present DECANTeR, a system to detect anomalous outbound HTTP communication, which passively extracts fingerprints for each application running on a monitored host. The goal of our system is to detect unknown malware and backdoor communication indicated by unknown fingerprints extracted from a host's network traffic. We evaluate a prototype with realistic data from an international organization and datasets composed of malicious traffic. We show that our system achieves a false positive rate of 0.9% for 441 monitored host machines, an average detection rate of 97.7%, and that it cannot be evaded by malware using simple evasion techniques such as using known browser user agent values. We compare our solution with DUMONT [24], the current state-of-the-art IDS which detects HTTP covert communication channels by focusing on benign HTTP traffic. The results show that DECANTeR outperforms DUMONT in terms of detection rate, false positive rate, and even evasion-resistance. Finally, DECANTeR detects 96.8% of information stealers in our dataset, which shows its potential to detect data exfiltration.
Collecting and analyzing personal data is important in modern information applications. Though the privacy of data providers should be protected, some adversarial users may behave badly under circumstances where they are not identified. However, the privacy of honest users should not be infringed. Thus, detecting anomalies without revealing normal users-identities is quite important for operating information systems using personal data. Though various methods of statistics and machine learning have been developed for detecting anomalies, it is difficult to know in advance what anomaly will come up. Thus, it would be useful to provide a "general" framework that can employ any anomaly detection method regardless of the type of data and the nature of the abnormality. In this paper, we propose a privacy preserving anomaly detection framework that allows an authority to detect adversarial users while other honest users are kept anonymous. By using cryptographic techniques, group signatures with message-dependent opening (GS-MDO) and public key encryption with non-interactive opening (PKENO), we provide a correspondence table that links a user and data in a secure way, and we can employ any anonymization technique and any anomaly detection method. It is particularly worth noting that no big brother exists, meaning that no single entity can identify users, while bad behaviors are always traceable. We also show the result of implementing our framework. Briefly, the overhead of our framework is on the order of dozens of milliseconds.
The detection of cyber-attacks has become a crucial task for highly sophisticated systems like industrial control systems (ICS). These systems are an essential part of critical information infrastructure. Therefore, we can highlight their vital role in contemporary society. The effective and reliable ICS cyber defense is a significant challenge for the cyber security community. Thus, intrusion detection is one of the demanding tasks for the cyber security researchers. In this article, we examine classification problem. The proposed detection system is based on supervised anomaly detection techniques. Moreover, we utilized classifiers algorithms in order to increase intrusion detection capabilities. The fusion of the classifiers is the way how to achieve the predefined goal.
We outline an anomaly detection method for industrial control systems (ICS) that combines the analysis of network package contents that are transacted between ICS nodes and their time-series structure. Specifically, we take advantage of the predictable and regular nature of communication patterns that exist between so-called field devices in ICS networks. By observing a system for a period of time without the presence of anomalies we develop a base-line signature database for general packages. A Bloom filter is used to store the signature database which is then used for package content level anomaly detection. Furthermore, we approach time-series anomaly detection by proposing a stacked Long Short Term Memory (LSTM) network-based softmax classifier which learns to predict the most likely package signatures that are likely to occur given previously seen package traffic. Finally, by the inspection of a real dataset created from a gas pipeline SCADA system, we show that an anomaly detection scheme combining both approaches can achieve higher performance compared to various current state-of-the-art techniques.
Cyber-physical systems are found in industrial and production systems, as well as critical infrastructures. Due to the increasing integration of IP-based technology and standard computing devices, the threat of cyber-attacks on cyber-physical systems has vastly increased. Furthermore, traditional intrusion defense strategies for IT systems are often not applicable in operational environments. In this paper we present an anomaly-based approach for detection and classification of attacks in cyber-physical systems. To test our approach, we set up a test environment with sensors, actuators and controllers widely used in industry, thus, providing system data as close as possible to reality. First, anomaly detection is used to define a model of normal system behavior by calculating outlier scores from normal system operations. This valid behavior model is then compared with new data in order to detect anomalies. Further, we trained an attack model, based on supervised attacks against the test setup, using the naive Bayes classifier. If an anomaly is detected, the classification process tries to classify the anomaly by applying the attack model and calculating prediction confidences for trained classes. To evaluate the statistical performance of our approach, we tested the model by applying an unlabeled dataset, which contains valid and anomalous data. The results show that this approach was able to detect and classify such attacks with satisfactory accuracy.