Fatemeh Deldar; Mahdi Abadi; Mohammad Ebrahimifard
Abstract
With the widespread use of Android smartphones, the Android platform has become an attractive target for cybersecurity attackers and malware authors. Meanwhile, the growing emergence of zero-day malware has long been a major concern for cybersecurity researchers. This is because malware that has not ...
Read More
With the widespread use of Android smartphones, the Android platform has become an attractive target for cybersecurity attackers and malware authors. Meanwhile, the growing emergence of zero-day malware has long been a major concern for cybersecurity researchers. This is because malware that has not been seen before often exhibits new or unknown behaviors, and there is no documented defense against it. In recent years, deep learning has become the dominant machine learning technique for malware detection and could achieve outstanding achievements. Currently, most deep malware detectiontechniques are supervised in nature and require training on large datasets of benign and malicious samples. However, supervised techniques usually do not perform well against zero-day malware. Semi-supervised and unsupervised deep malware detection techniques have more potential to detect previously unseen malware. In this paper, we present MalGAE, a novel end-to-end deep malware detection technique that leverages one-class graph neural networks to detect Android malware in a semi-supervised manner. MalGAE represents each Android application with an attributed function call graph (AFCG) to benefit the ability of graphs to model complex relationships between data. It builds a deep one-class classifier by training a stacked graph autoencoder with graph convolutional layers on benign AFCGs. Experimental results show that MalGAE can achieve good detection performance in terms of different evaluation measures.
F. Barani; M. Abadi
Abstract
Mobile ad hoc networks (MANETs) are multi-hop wireless networks of mobile nodes constructed dynamically without the use of any fixed network infrastructure. Due to inherent characteristics of these networks, malicious nodes can easily disrupt the routing process. A traditional approach to detect such ...
Read More
Mobile ad hoc networks (MANETs) are multi-hop wireless networks of mobile nodes constructed dynamically without the use of any fixed network infrastructure. Due to inherent characteristics of these networks, malicious nodes can easily disrupt the routing process. A traditional approach to detect such malicious network activities is to build a profile of the normal network traffic, and then identify an activity as suspicious if it deviates from this profile. As the topology of a MANET constantly changes over time, the simple use of a static profile is not efficient. In this paper, we present a dynamic hybrid approach based on the artificial bee colony (ABC) and negative selection (NS) algorithms, called BeeID, for intrusion detection in AODV-based MANETs. The approach consists of three phases: training, detection, and updating. In the training phase, a niching artificial bee colony algorithm, called NicheNABC, runs a negative selection algorithm multiple times to generate a set of mature negative detectors to cover the nonself space. In the detection phase, mature negative detectors are used to discriminate between normal and malicious network activities. In the updating phase, the set of mature negative detectors is updated by one of two methods of partial updating or total updating. We use the Monte Carlo integration to estimate the amount of the nonself space covered by negative detectors and to determine when the total updating should be done. We demonstrate the effectiveness of BeeID for detecting several types of routing attacks on AODV-based MANETs simulated using the NS2 simulator. The experimental results show that BeeID can achieve a better tradeoff between detection rate and false-alarm rate as compared to other dynamic approaches previously reported in the literature.
M. Yahyazadeh; M. Abadi
Abstract
Botnets are recognized as one of the most dangerous threats to the Internet infrastructure. They are used for malicious activities such as launching distributed denial of service attacks, sending spam, and leaking personal information. Existing botnet detection methods produce a number of good ideas, ...
Read More
Botnets are recognized as one of the most dangerous threats to the Internet infrastructure. They are used for malicious activities such as launching distributed denial of service attacks, sending spam, and leaking personal information. Existing botnet detection methods produce a number of good ideas, but they are far from complete yet, since most of them cannot detect botnets in an early stage of their lifecycle; moreover, they depend on a particular command and control (C&C) protocol. In this paper, we address these issues and propose an online unsupervised method, called BotOnus, for botnet detection that does not require a priori knowledge of botnets. It extracts a set of flow feature vectors from the network traffic at the end of each time period, and then groups them to some flow clusters by a novel online fixed-width clustering algorithm. Flow clusters that have at least two members, and their intra-cluster similarity is above a similarity threshold, are identified as suspicious botnet clusters, and all hosts in such clusters are identified as bot infected. We demonstrate the effectiveness of BotOnus to detect various botnets including HTTP-, IRC-, and P2P-based botnets using a testbed network. The results of experiments show that it can successfully detect various botnets with an average detection rate of 94.33% and an average false alarm rate of 3.74%.
M. Abadi; S. Jalili
Abstract
To prevent an exploit, the security analyst must implement a suitable countermeasure. In this paper, we consider cost-sensitive attack graphs (CAGs) for network vulnerability analysis. In these attack graphs, a weight is assigned to each countermeasure to represent the cost of its implementation. There ...
Read More
To prevent an exploit, the security analyst must implement a suitable countermeasure. In this paper, we consider cost-sensitive attack graphs (CAGs) for network vulnerability analysis. In these attack graphs, a weight is assigned to each countermeasure to represent the cost of its implementation. There may be multiple countermeasures with different weights for preventing a single exploit. Also, a single countermeasure may prevent multiple exploits. We present a binary particle swarm optimization algorithm with a time-varying velocity clamping, called SwarmCAG-TVVC, for minimization analysis of cost-sensitive attack graphs. The aim is to find a critical set of countermeasures with minimum weight whose implementation causes the initial nodes and the goal nodes of the graph to be completely disconnected. This problem is in fact a constrained optimization problem. A repair method is used to convert the constrained optimization problem into an unconstrained one. A local search heuristic is used to improve the overall performance of the algorithm. We compare the performance of SwarmCAG-TVVC with a greedy algorithm GreedyCAG and a genetic algorithm GenNAG for minimization analysis of several large-scale cost-sensitive attack graphs. On average, the weight of a critical set of countermeasures found by SwarmCAG-TVVC is 6.15 percent less than the weight of a critical set of countermeasures found by GreedyCAG. Also, SwarmCAG-TVVC performs better than GenNAG in terms of convergence speed and accuracy. The results of the experiments show that SwarmCAG-TVVC can be successfully used for minimization analysis of large-scale cost-sensitive attack graphs.