158 citations · 461 across the 37 of their papers we have counts for
38 papers
SAGEGAN: Style-Based Anomaly Detection with Gaussian Embeddings using Generative Adversarial Networks
Thesath Wijayasiri, Kar Wai Fok, Vrizlynn L. L. Thing
Malware evolves faster than rule-based and signature-driven detection pipelines. This paper presents SAGEGAN, a benign-only trained malware anomaly detection framework that convert…
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
Zihao Wang, Yiming Li, Yutong Wu +8
LLM-based web agents are increasingly deployed in real-world settings such as e-commerce, where they interact extensively with untrusted web content while executing actions that ca…
Explaining Intrusion Alert Decisions of Deep Learning-based Network Intrusion Detection Systems for Security Analysts
Ayush Kumar, Vrizlynn L. L. Thing
In this paper, we present EXP-SEC, a novel framework which can explain the intrusion detection decisions of DL-based NIDS (which lead to security alerts) in a way that is aligned w…
HilEnT: Hilbert, Entropy Transformed Image Based Malware Detection
Rahul Kale, Thesath Wijayasiri, Kar Wai Fok +1
With the increasing threat of malware across various software related domains, malware detection and classification is critical to determine the response actions. Different strateg…
TIER: Trajectory-Invariant Explanation Regularization for Membership Privacy
Varun Sharma, Kar Wai Fok, Vrizlynn L. L. Thing
Explainability is central to building trustworthy AI, yet explanation interfaces can inadvertently provide adversaries with an expanded privacy-related attack surfaces. Recent stud…
DE-FIVE: Detecting Malicious Image Prompts via Fourier Features and Image Vector Embeddings
Xingwei Zhong, Varun Sharma, Kar Wai Fok +1
Vision language models (VLMs) employ both visual and textual modalities to enable advanced vision-language inference. However, incorporating visual modalities expands the attack su…
DefenSee: Dissecting Threat from Sight and Text -- A Multi-View Defensive Pipeline for Multi-modal Jailbreaks
Zihao Wang, Kar Wai Fok, Vrizlynn L. L. Thing
Multi-modal large language models (MLLMs), capable of processing text, images, and audio, have been widely adopted in various AI applications. However, recent MLLMs integrating ima…
Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
Xingwei Zhong, Kar Wai Fok, Vrizlynn L. L. Thing
Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues,…
CoSPED: Consistent Soft Prompt Targeted Data Extraction and Defense
Zhuochen Yang, Kar Wai Fok, Vrizlynn L. L. Thing
Large language models have gained widespread attention recently, but their potential security vulnerabilities, especially privacy leakage, are also becoming apparent. To test and e…
ExpIDS: A Drift-adaptable Network Intrusion Detection System With Improved Explainability
Ayush Kumar, Kar Wai Fok, Vrizlynn L. L. Thing
Despite all the advantages associated with Network Intrusion Detection Systems (NIDSs) that utilize machine learning (ML) models, there is a significant reluctance among cyber secu…
A Survey of Transaction Tracing Techniques for Blockchain Systems
Ayush Kumar, Vrizlynn L. L. Thing
With the proliferation of new blockchain-based cryptocurrencies/assets and platforms that make it possible to transact across them, it becomes important to consider not just whethe…
Enhanced Consistency Bi-directional GAN (CBiGAN) for Malware Anomaly Detection
Thesath Wijayasiri, Kar Wai Fok, Vrizlynn L. L. Thing
Static malware analysis remains a core technique in cybersecurity due to its ability to assess potentially malicious software without execution. Nevertheless, many existing static…
Network Attack Traffic Detection With Hybrid Quantum-Enhanced Convolution Neural Network
Zihao Wang, Kar Wai Fok, Vrizlynn L. L. Thing
The emerging paradigm of Quantum Machine Learning (QML) combines features of quantum computing and machine learning (ML). QML enables the generation and recognition of statistical…
Evaluating The Explainability of State-of-the-Art Deep Learning-based Network Intrusion Detection Systems
Ayush Kumar, Vrizlynn L. L. Thing
State-of-the-art deep learning (DL)-based network intrusion detection systems (NIDSs) offer limited "explainability". For example, how do they make their decisions? Do they suffer…
CPE-Identifier: Automated CPE identification and CVE summaries annotation with Deep Learning and NLP
Wanyu Hu, Vrizlynn L. L. Thing
With the drastic increase in the number of new vulnerabilities in the National Vulnerability Database (NVD) every year, the workload for NVD analysts to associate the Common Platfo…
Privacy-Preserving Intrusion Detection using Convolutional Neural Networks
Martin Kodys, Zhongmin Dai, Vrizlynn L. L. Thing
Privacy-preserving analytics is designed to protect valuable assets. A common service provision involves the input data from the client and the model on the analyst's side. The imp…
Enhancing Network Intrusion Detection Performance using Generative Adversarial Networks
Xinxing Zhao, Kar Wai Fok, Vrizlynn L. L. Thing
Network intrusion detection systems (NIDS) play a pivotal role in safeguarding critical digital infrastructures against cyber threats. Machine learning-based detection models appli…
Privacy preserving layer partitioning for Deep Neural Network models
Kishore Rajasekar, Randolph Loh, Kar Wai Fok +1
MLaaS (Machine Learning as a Service) has become popular in the cloud computing domain, allowing users to leverage cloud resources for running private inference of ML models on the…
Exploring Emerging Trends in 5G Malicious Traffic Analysis and Incremental Learning Intrusion Detection Strategies
Zihao Wang, Kar Wai Fok, Vrizlynn L. L. Thing
The popularity of 5G networks poses a huge challenge for malicious traffic detection technology. The reason for this is that as the use of 5G technology increases, so does the risk…
An adversarial attack approach for eXplainable AI evaluation on deepfake detection models
Balachandar Gowrisankar, Vrizlynn L. L. Thing
With the rising concern on model interpretability, the application of eXplainable AI (XAI) tools on deepfake detection models has been a topic of interest recently. In image classi…
Malicious Lateral Movement in 5G Core With Network Slicing And Its Detection
Ayush Kumar, Vrizlynn L. L. Thing
5G networks are susceptible to cyber attacks due to reasons such as implementation issues and vulnerabilities in 3GPP standard specifications. In this work, we propose lateral move…
A Public Key Infrastructure for 5G Service-Based Architecture
Ayush Kumar, Vrizlynn L. L. Thing
The 3GPP 5G Service-based Architecture (SBA) security specifications leave several details on how to setup an appropriate Public Key Infrastructure (PKI) for 5G SBA, unspecified. I…
Enhancing Cyber-Resilience in Self-Healing Cyber-Physical Systems with Implicit Guarantees
Randolph Loh, Vrizlynn L. L. Thing
Self-Healing Cyber-Physical Systems (SH-CPS) effectively recover from system perceived failures without human intervention. They ensure a level of resilience and tolerance to unfor…
Few-shot Weakly-supervised Cybersecurity Anomaly Detection
Rahul Kale, Vrizlynn L. L. Thing
With increased reliance on Internet based technologies, cyberattacks compromising users' sensitive data are becoming more prevalent. The scale and frequency of these attacks are es…