arXiv subjects

Ian Welch

Publications and source records attributed to Ian Welch.

5 recordsLinked to original sources

arXiv2024

Relation-aware based Siamese Denoising Autoencoder for Malware Few-shot Classification

When malware employs an unseen zero-day exploit, traditional security measures such as vulnerability scanners and antivirus software can fail to detect them. This is because these tools rely on known patches and signatures, which do not exist for new zero-day attacks. Furthermore, existing machine learning methods, which are trained on specific and occasionally outdated malware samples, may struggle to adapt to features in new malware. To address this issue, there is a need for a more robust machine learning model that can identify relationships between malware samples without being trained on a particular malware feature set. This is particularly crucial in the field of cybersecurity, where the number of malware samples is limited and obfuscation techniques are widely used. Current approaches using stacked autoencoders aim to remove the noise introduced by obfuscation techniques through reconstruction of the input. However, this approach ignores the semantic relationships between features across different malware samples. To overcome this limitation, we propose a novel Siamese Neural Network (SNN) that uses relation-aware embeddings to calculate more accurate similarity probabilities based on semantic details of different malware samples. In addition, by using entropy images as inputs, our model can extract better structural information and subtle differences in malware signatures, even in the presence of obfuscation techniques. Evaluations on two large malware sample sets using the N-shot and N-way methods show that our proposed model is highly effective in predicting previously unseen malware, even in the presence of obfuscation techniques.

cs.CR↗

arXiv2022

Malware Triage Approach using a Task Memory based on Meta-Transfer Learning Framework

To enhance the efficiency of incident response triage operations, it is not cost-effective to defend all systems equally in a complex cyber environment. Instead, prioritizing the defense of critical functionality and the most vulnerable systems is desirable. Threat intelligence is crucial for guiding Security Operations Center (SOC) analysts' focus toward specific system activity and provides the primary contextual foundation for interpreting security alerts. This paper explores novel approaches for improving incident response triage operations, including dealing with attacks and zero-day malware. This solution for rapid prioritization of different malware have been raised to formulate fast response plans to minimize socioeconomic damage from the massive growth of malware attacks in recent years, it can also be extended to other incident response. We propose a malware triage approach that can rapidly classify and prioritize different malware classes to address this concern. We utilize a pre-trained ResNet18 network based on Siamese Neural Network (SNN) to reduce the biases in weights and parameters. Furthermore, our approach incorporates external task memory to retain the task information of previously encountered examples. This helps to transfer experience to new samples and reduces computational costs, without requiring backpropagation on external memory. Evaluation results indicate that the classification aspect of our proposed method surpasses other similar classification techniques in terms of performance. This new triage strategy based on task memory with meta-learning evaluates the level of similarity matching across malware classes to identify any risky and unknown malware (e.g., zero-day attacks) so that a defense of those that support critical functionality can be conducted.

cs.CR↗

arXiv2021

A Few-Shot Meta-Learning based Siamese Neural Network using Entropy Features for Ransomware Classification

Ransomware defense solutions that can quickly detect and classify different ransomware classes to formulate rapid response plans have been in high demand in recent years. Though the applicability of adopting deep learning techniques to provide automation and self-learning provision has been proven in many application domains, the lack of data available for ransomware (and other malware)samples has been raised as a barrier to developing effective deep learning-based solutions. To address this concern, we propose a few-shot meta-learning based Siamese Neural Network that not only detects ransomware attacks but is able to classify them into different classes. Our proposed model utilizes the entropy feature directly extracted from ransomware binary files to retain more fine-grained features associated with different ransomware signatures. These entropy features are used further to train and optimize our model using a pre-trained network (e.g. VGG-16) in a meta-learning fashion. This approach generates more accurate weight factors, compared to feature images are used, to avoid the bias typically associated with a model trained with a limited number of training samples. Our experimental results show that our proposed model is highly effective in providing a weighted F1-score exceeding the rate>86% compared

cs.CR↗

arXiv2021

A Survey on Threat Situation Awareness Systems: Framework, Techniques, and Insights

Cyberspace is full of uncertainty in terms of advanced and sophisticated cyber threats which are equipped with novel approaches to learn the system and propagate themselves, such as AI-powered threats. To debilitate these types of threats, a modern and intelligent Cyber Situation Awareness (SA) system need to be developed which has the ability of monitoring and capturing various types of threats, analyzing and devising a plan to avoid further attacks. This paper provides a comprehensive study on the current state-of-the-art in the cyber SA to discuss the following aspects of SA: key design principles, framework, classifications, data collection, and analysis of the techniques, and evaluation methods. Lastly, we highlight misconceptions, insights and limitations of this study and suggest some future work directions to address the limitations.

cs.CR↗

arXiv2019

Automatic Device Selection and Access PolicyGeneration based on User Preference for IoTActivity Workflow

The emerging Internet of Things (IoT) has lead to a dramatic increase in type, quantity, and the number of functions that can be offered in a smart environment. Future smart environments will be even richer in terms of the number of devices and functionality provided by them. This poses two major challenges a) an end user has to search through a vast number of IoT devices to identify the suitable devices that satisfy their preferences, and b) it is extremely difficult for users to manually define fine-grained security policies to support workflows involving multiple functions. This paper introduces an intelligent new approach to overcome these challenges by a) enabling users to describe their required functionalities in the form of activity workflow, b) automatically selecting a group of devices to satisfy users functional requirements and maximise their preferences over device usage, c) systematically generating local network access control policies to ensure enforce the principle of least privilege. We study different heuristic search algorithms to find the preferred devices for a given workflow. Experiments results show that the Genetic Algorithm is the best, among the algorithms that we test, as it offers a balance between efficiency and effectiveness.

cs.CR↗