- Electrical and Electronic Engineering - Research Publications
Electrical and Electronic Engineering - Research Publications
Permanent URI for this collection
8 results
Filters
Reset filtersSettings
Statistics
Citations
Search Results
Now showing
1 - 8 of 8
-
ItemNo Preview AvailableA Group Formation Game for Local Anomaly DetectionYe, Z ; Alpcan, T ; Leckie, C (IEEE, 2023-01-01)
-
ItemNo Preview AvailableRobust Wireless Network Anomaly Detection with Collaborative Adversarial AutoencodersKatzef, M ; Cullen, AC ; Alpcan, T ; Leckie, C (IEEE, 2023)
-
ItemNo Preview AvailableOnline Trajectory Anomaly Detection Based on Intention OrientationWang, C ; Erfani, S ; Alpcan, T ; Leckie, C (IEEE, 2023-01-01)
-
ItemNo Preview AvailableWireless Network Simulation to Create Machine Learning Benchmark DataKatzef, M ; Cullen, AC ; Alpcan, T ; Leckie, C ; Kopacz, J (IEEE, 2022-01-01)
-
ItemNo Preview AvailableLocal Intrinsic Dimensionality Signals Adversarial PerturbationsWeerasinghe, S ; Abraham, T ; Alpcan, T ; Erfani, SM ; Leckie, C ; Rubinstein, BIP (IEEE, 2022)
-
ItemNo Preview AvailableGenerative Adversarial Networks for anomaly detection on decentralised dataKatzefa, M ; Cullen, AC ; Alpcan, T ; Leckie, C (PERGAMON-ELSEVIER SCIENCE LTD, 2022)
-
ItemDetection of Anomalous Communications with SDRs and Unsupervised Adversarial LearningWeerasinghe, S ; Erfani, SM ; Alpcan, T ; Leckie, C ; Riddle, J ; Cherkaoui, S ; Andersson, K ; AlTurjman, F (IEEE, 2019-02-08)Software-defined radios (SDRs) with substantial cognitive (computing) and networking capabilities provide an opportunity for observing radio communications in an area and potentially identifying malicious rogue agents. Assuming a prevalence of encryption methods, a cognitive network of such SDRs can be used as a low-cost and flexible scanner/sensor array for distributed detection of anomalous communications by focusing on their statistical characteristics. Identifying rogue agents based on their wireless communications patterns is not a trivial task, especially when they deliberately try to mask their activities. We address this problem using a novel framework that utilizes adversarial learning, non-linear data transformations to minimize the rogue agent's attempts at masking their activities, and game theory to predict the behavior of rogue agents and take the necessary countermeasures.
-
ItemSupport vector machines resilient against training data integrity attacksWeerasinghe, S ; Erfani, SM ; Alpcan, T ; Leckie, C (Elsevier BV, 2019-12-01)Support Vector Machines (SVMs) are vulnerable to integrity attacks, where malicious attackers distort the training data in order to compromise the decision boundary of the learned model. With increasing real-world applications of SVMs, malicious data that is classified as innocuous may have harmful consequences. This paper presents a novel framework that utilizes adversarial learning, nonlinear data projections, and game theory to improve the resilience of SVMs against such training-data-integrity attacks. The proposed approach introduces a layer of uncertainty through the use of random projections on top of the learners, making it challenging for the adversary to guess the specific configurations of the learners. To find appropriate projection directions, we introduce novel indices that ensure the contraction of the data and maximize the detection accuracy. Experiments with benchmark data sets show increases in detection rates up to 13.5% for OCSVMs and up to 14.1% for binary SVMs under different attack algorithms when compared with the respective base algorithms.