2 November 2021 in Journal of Network and Systems Management
28 March 2020 in Neural Computing and Applications
3 October 2024 in ACM Computing Surveys
In the past decade, the number of malware variants has increased rapidly. Many researchers have proposed to detect malware using intelligent techniques, such as Machine Learning (ML) and Deep Learning (DL), which have high accuracy and precision. These methods, however, suffer from being opaque in the decision-making process. Therefore, we need Artificial Intelligence (AI)-based models to be explainable, interpretable, and transparent to be reliable and trustworthy. In this survey, we reviewed articles related to Explainable AI (XAI) and their application to the significant scope of malware detection. The article encompasses a comprehensive examination of various XAI algorithms employed in malware analysis. Moreover, we have addressed the characteristics, challenges, and requirements in malware analysis that cannot be accommodated by standard XAI methods. We discussed that even though Explainable Malware Detection (EMD) models provide explainability, they make an AI-based model more vulnerable to adversarial attacks. We also propose a framework that assigns a level of explainability to each XAI malware analysis model, based on the security features involved in each method. In summary, the proposed project focuses on combining XAI and malware analysis to apply XAI models for scrutinizing the opaque nature of AI systems and their applications to malware analysis.
13 April 2023 in IEEE Transactions on Neural Networks and Learning Systems
Despite the potential deep learning (DL) algorithms have shown, their lack of transparency hinders their widespread application. Extracting if-then rules from deep neural networks is a powerful explanation method to capture nonlinear local behaviors. However, existing rule extraction methods suffer from inefficiency, incomprehensibility, infidelity, and not scaling well. Concerning security applications, they are not optimized regarding the decision boundary, data types and ranges, classification tasks, and dataset size. In this article, we propose CapsRule, an effective and efficient rule-based DL explanation method dedicated to classifying network attacks. It extracts high-fidelity rules from the feed-forward capsule network that explains how an input sample is classified. Using precomputed coupling coefficients, the training phase overlaps the rule extraction process to increase efficiency. The activation vector of a capsule can represent semantic intelligence about the attributes of the input sample. The rules extracted from CapsRule address the major concerns of network attack detection. The rules: 1) approximate the nonlinear decision boundary of the underlying data; 2) reduce the number of false positives significantly; 3) increase transparency; and 4) help find errors and noise in the data. We evaluate CapsRule on the CICDDoS2019 dataset that contains over a million of the most advanced Distributed Denial-of-Service (DDoS) attacks. The extensive evaluation shows that it generates accurate, high-fidelity, and comprehensible rules. CapsRule achieves an average accuracy of 99.0% and a false positive rate of 0.70% for reflection-and exploitation-based attacks. We verify that the learned features from the rulesets match our domain-specific knowledge. They also help find flaws in the dataset generation process and erroneous patterns caused by attack simulators.
20 December 2019 in IEEE Access
Fog-enhanced IoT (Internet of Things) is a fast-growing technology in which many firms and industries are currently investing to develop their own real-time and low latency scenarios. Compared with the traditional IoT, fog-enhanced IoT can offer a higher level of efficiency and stronger security by providing local data pre-processing, filtering, and forwarding mechanisms. However, fog-enhanced IoT faces some security and privacy challenges, since fog nodes are deployed at the network edge and may not be fully trustable. In this paper, we present a new privacy-preserving subset aggregation scheme, called PPSA, in fog-enhanced IoT scenarios, that enables a query user to gain the sum of data from a subset of IoT devices. To identify the subset, inner product similarity of the normalized vectors in the query user side and each IoT device is securely computed. If the inner product is greater than the user’s specified threshold, IoT device’s data will be privately aggregated to form the final response. To successfully launch privacy-preserving subset aggregation in the proposed scheme, we employ the Paillier homomorphic encryption to encrypt user’s attribute vector, similarity threshold, IoT end-devices’ data, as well as the intermediate results. To the best of our knowledge, this work is the first one to address the privacy-preserving subset aggregation in fog-enhanced IoT. We analyze and extensively evaluate the efficiency and security of the proposed PPSA scheme, and the detailed analysis and results indicate that our proposed PPSA scheme can practically achieve privacy-preserving subset aggregation with significant communication and computational cost saving.
8 October 2021 in Journal of Network and Systems Management