arXiv subjects

Kar Wai Fok

Publications and source records attributed to Kar Wai Fok.

16 recordsLinked to original sources

arXiv2026

SAGEGAN: Style-Based Anomaly Detection with Gaussian Embeddings using Generative Adversarial Networks

Malware evolves faster than rule-based and signature-driven detection pipelines. This paper presents SAGEGAN, a benign-only trained malware anomaly detection framework that converts portable executable files into compact three-channel images and models benign structure through style-conditioned adversarial reconstruction. The representation combines Hilbert-mapped byte values, benign-referenced byte-transition surprise, and entropy deviation from benign software. The model encodes each image into a layer-wise style tensor aligned with a seven-stage modulated generator, rather than a single latent bottleneck. A Gaussian style prior, moment-based prior alignment, and latent consistency are used to reduce mismatch between encoded benign styles and the generator's sampled manifold. For interpretation, a deterministic encoder pathway maps each executable to a fixed style tensor, enabling repeatable layer-wise family distance, gradient sensitivity, principal component, and class-behaviour analyses. On a self-collected portable executable corpus containing malware from 214 families, the Gaussian variant achieves 89.76% area under the receiver operating characteristic curve and 88.19% balanced accuracy, while the genome-style variant reaches 88.03% and 84.09%, respectively. Without refitting model weights, benign reference statistics, or decision thresholds, the same checkpoints are evaluated on DIKE, Microsoft BIG 2015, and Lester malware subsets. The results suggest that layer-wise style modelling supports both anomaly ranking and structured post hoc analysis of how malware families depart from the benign manifold.

cs.CR↗

arXiv2026

HilEnT: Hilbert, Entropy Transformed Image Based Malware Detection

With the increasing threat of malware across various software related domains, malware detection and classification is critical to determine the response actions. Different strategies have been adopted to address the challenge of malware detection. With the advent of deep learning techniques, malware detection using image processing has garnered research attention. In this work, we proposed a novel malware binary to image transformation technique HilEnT based on a combination of Hilbert curve-based transformation of malware binary and the entropy feature comparison of malware file with benign and malware classes. Three grayscale images produced during this process are combined to form a three-channel colored image which is then used for malware detection using machine learning techniques. We performed supervised binary and multiclass classification to evaluate the effectiveness of our proposed HilEnT. We also evaluated a few-shot learning technique to assess the robustness of our proposed HilEnT in a practical setting where the number of available class samples is limited. Furthermore, we investigated the benefits of combination of Histogram of Oriented Gradients and Principal Component Analysis for time performance improvements through feature reduction techniques. We evaluated our proposed methodology on four datasets: Dike, Michael Lester Dataset, Microsoft BIG 2015 and a self-collected dataset, and achieved the state-of-the-art results.

cs.CR↗

arXiv2026

TIER: Trajectory-Invariant Explanation Regularization for Membership Privacy

Explainability is central to building trustworthy AI, yet explanation interfaces can inadvertently provide adversaries with an expanded privacy-related attack surfaces. Recent studies show that advanced membership-inference attacks succeed by exploiting confidence-drop trajectories, induced through attribution-guided perturbations, as discriminative features, rather than directly using confidence scores or explanation vectors. Existing defenses against membership inference fail to directly mitigate such explanation-driven attacks. In this work, we investigate whether, during training, a model's own gradients can be leveraged as defense signals against such attacks, thereby aligning explanation profiles between members and non-members. To this end, we propose a Trajectory-Invariant Explanation Regularization (TIER) defense that penalizes erratic fluctuations in confidence drops simulated through gradient-guided perturbations and simultaneously minimizes the distributional shifts via KL-divergence. Unlike conventional adversarial training, which emphasizes label robustness, our approach targets explanation robustness by enforcing self-consistency through KL-divergence and reducing the variance of confidence drops between members and non-members. Extensive experiments confirm that our method effectively mitigates these attacks, delivering privacy protection while maintaining model utility and explanation fidelity.

cs.CR↗

arXiv2026

DE-FIVE: Detecting Malicious Image Prompts via Fourier Features and Image Vector Embeddings

Vision language models (VLMs) employ both visual and textual modalities to enable advanced vision-language inference. However, incorporating visual modalities expands the attack surface of VLMs, making them more susceptible to security threats such as adversarial perturbations and indirect prompt injection, wherein crafted malicious image prompts can elicit unintended model outputs. Existing defense methods against malicious image prompts remain insufficient as they typically demand extensive datasets for retraining or the deployment of additional, complex classifiers. Most critically, there is a profound lack of specialized defense mechanisms specifically targeting indirect prompt injections, a gap that serves as a primary motivation for this work. To address these limitations, we introduce DE-FIVE, a novel training-free framework for detecting malicious image prompts by leveraging Fourier features and the hidden state representations of the visual encoder (image vector embeddings) across perturbations. Specifically, we develop a hybrid detection strategy consisting of a black-box detector that operates on Fourier-domain features and a white-box detector that exploits image vector embeddings derived from only a few-shot malicious set. Extensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art baselines against malicious image prompts.

cs.CR↗

arXiv2026

Enhanced Consistency Bi-directional GAN (CBiGAN) for Malware Anomaly Detection

Static malware analysis remains a core technique in cybersecurity due to its ability to assess potentially malicious software without execution. Nevertheless, many existing static approaches rely on handcrafted features or curated datasets that may not generalize well to evolving malware distributions. In this work, we investigate an alternative representation that operates directly on raw binary content. Executable files are transformed into visual encodings that preserve local structural relationships, enabling the use of deep learning models without requiring semantic disassembly or dynamic behavior profiling. This study explores the use of a Consistency Bi-directional Generative Adversarial Network (CBi-GAN) as an anomaly detection framework rather than as a generative model. The method enforces consistency between latent encodings and reconstructions, allowing deviations from learned benign structure to be quantified through reconstruction discrepancies. Importantly, the approach does not introduce a new generative architecture, instead, it evaluates how consistency based generative modeling can be applied at scale to heterogeneous malware data. The proposed framework is evaluated across multiple datasets comprising both Portable Executable (PE) and Object Linking and Embedding (OLE) files, including a large self-collected corpus spanning 214 malware families. Results demonstrate stable detection performance in terms of Area Under the Curve (AUC) while maintaining a unified and computationally lightweight processing pipeline. These findings suggest that consistency based generative modeling provides a practical and scalable direction for malware anomaly detection across diverse file formats and threat families.

cs.CR↗

arXiv2026

CoSPED: Consistent Soft Prompt Targeted Data Extraction and Defense

Large language models have gained widespread attention recently, but their potential security vulnerabilities, especially privacy leakage, are also becoming apparent. To test and evaluate for data extraction risks in LLM, we proposed CoSPED, short for Consistent Soft Prompt targeted data Extraction and Defense. We introduce several innovative components, including Dynamic Loss, Additive Loss, Common Loss, and Self Consistency Decoding Strategy, and tested to enhance the consistency of the soft prompt tuning process. Through extensive experimentation with various combinations, we achieved an extraction rate of 65.2% at a 50-token prefix comparison. Our comparisons of CoSPED with other reference works confirm our superior extraction rates. We evaluate CoSPED on more scenarios, achieving Pythia model extraction rate of 51.7% and introducing cross-model comparison. Finally, we explore defense through Rank-One Model Editing and achieve a reduction in the extraction rate to 1.6%, which proves that our analysis of extraction mechanisms can directly inform effective mitigation strategies against soft prompt-based attacks.

cs.CR↗

arXiv2025

DefenSee: Dissecting Threat from Sight and Text -- A Multi-View Defensive Pipeline for Multi-modal Jailbreaks

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 images and text remain highly vulnerable to coordinated jailbreaks. Existing defenses primarily focus on the text, lacking robust multi-modal protection. As a result, studies indicate that MLLMs are more susceptible to malicious or unsafe instructions, unlike their text-only counterparts. In this paper, we proposed DefenSee, a robust and lightweight multi-modal black-box defense technique that leverages image variants transcription and cross-modal consistency checks, mimicking human judgment. Experiments on popular multi-modal jailbreak and benign datasets show that DefenSee consistently enhances MLLM robustness while better preserving performance on benign tasks compared to SOTA defenses. It reduces the ASR of jailbreak attacks to below 1.70% on MiniGPT4 using the MM-SafetyBench benchmark, significantly outperforming prior methods under the same conditions.

cs.CR↗

arXiv2025

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses

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, such as jailbreak attacks that alter the model's input to induce unauthorized or harmful responses. The incorporation of the additional visual modality introduces new dimensions to security threats. In this paper, we proposed a black-box jailbreak method via both text and image prompts to evaluate MLLMs. In particular, we designed text prompts with provocative instructions, along with image prompts that introduced mutation and multi-image capabilities. To strengthen the evaluation, we also designed a Re-attack strategy. Empirical results show that our proposed work can improve capabilities to assess the security of both open-source and closed-source MLLMs. With that, we identified gaps in existing defense methods to propose new strategies for both training-time and inference-time defense methods, and evaluated them across the new jailbreak methods. The experiment results showed that the re-designed defense methods improved protections against the jailbreak attacks.

cs.CR↗

arXiv2025

ExpIDS: A Drift-adaptable Network Intrusion Detection System With Improved Explainability

Despite all the advantages associated with Network Intrusion Detection Systems (NIDSs) that utilize machine learning (ML) models, there is a significant reluctance among cyber security experts to implement these models in real-world production settings. This is primarily because of their opaque nature, meaning it is unclear how and why the models make their decisions. In this work, we design a deep learning-based NIDS, ExpIDS to have high decision tree explanation fidelity, i.e., the predictions of decision tree explanation corresponding to ExpIDS should be as close to ExpIDS's predictions as possible. ExpIDS can also adapt to changes in network traffic distribution (drift). With the help of extensive experiments, we verify that ExpIDS achieves higher decision tree explanation fidelity and a malicious traffic detection performance comparable to state-of-the-art NIDSs for common attacks with varying levels of real-world drift.

cs.CR↗

arXiv2025

Network Attack Traffic Detection With Hybrid Quantum-Enhanced Convolution Neural Network

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 data patterns that classical computers and classical ML methods struggle to effectively execute. QML utilizes quantum systems to enhance algorithmic computation speed and real-time data processing capabilities, making it one of the most promising tools in the field of ML. Quantum superposition and entanglement features also hold the promise to potentially expand the potential feature representation capabilities of ML. Therefore, in this study, we explore how quantum computing affects ML and whether it can further improve the detection performance on network traffic detection, especially on unseen attacks which are types of malicious traffic that do not exist in the ML training dataset. Classical ML models often perform poorly in detecting these unseen attacks because they have not been trained on such traffic. Hence, this paper focuses on designing and proposing novel hybrid structures of Quantum Convolutional Neural Network (QCNN) to achieve the detection of malicious traffic. The detection performance, generalization, and robustness of the QML solutions are evaluated and compared with classical ML running on classical computers. The emphasis lies in assessing whether the QML-based malicious traffic detection outperforms classical solutions. Based on experiment results, QCNN models demonstrated superior performance compared to classical ML approaches on unseen attack detection.

cs.CR↗

arXiv2024

Privacy preserving layer partitioning for Deep Neural Network models

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 their data. However, ensuring user input privacy and secure inference execution is essential. One of the approaches to protect data privacy and integrity is to use Trusted Execution Environments (TEEs) by enabling execution of programs in secure hardware enclave. Using TEEs can introduce significant performance overhead due to the additional layers of encryption, decryption, security and integrity checks. This can lead to slower inference times compared to running on unprotected hardware. In our work, we enhance the runtime performance of ML models by introducing layer partitioning technique and offloading computations to GPU. The technique comprises two distinct partitions: one executed within the TEE, and the other carried out using a GPU accelerator. Layer partitioning exposes intermediate feature maps in the clear which can lead to reconstruction attacks to recover the input. We conduct experiments to demonstrate the effectiveness of our approach in protecting against input reconstruction attacks developed using trained conditional Generative Adversarial Network(c-GAN). The evaluation is performed on widely used models such as VGG-16, ResNet-50, and EfficientNetB0, using two datasets: ImageNet for Image classification and TON IoT dataset for cybersecurity attack detection.

cs.CR↗

arXiv2024

Enhancing Network Intrusion Detection Performance using Generative Adversarial Networks

Network intrusion detection systems (NIDS) play a pivotal role in safeguarding critical digital infrastructures against cyber threats. Machine learning-based detection models applied in NIDS are prevalent today. However, the effectiveness of these machine learning-based models is often limited by the evolving and sophisticated nature of intrusion techniques as well as the lack of diverse and updated training samples. In this research, a novel approach for enhancing the performance of an NIDS through the integration of Generative Adversarial Networks (GANs) is proposed. By harnessing the power of GANs in generating synthetic network traffic data that closely mimics real-world network behavior, we address a key challenge associated with NIDS training datasets, which is the data scarcity. Three distinct GAN models (Vanilla GAN, Wasserstein GAN and Conditional Tabular GAN) are implemented in this work to generate authentic network traffic patterns specifically tailored to represent the anomalous activity. We demonstrate how this synthetic data resampling technique can significantly improve the performance of the NIDS model for detecting such activity. By conducting comprehensive experiments using the CIC-IDS2017 benchmark dataset, augmented with GAN-generated data, we offer empirical evidence that shows the effectiveness of our proposed approach. Our findings show that the integration of GANs into NIDS can lead to enhancements in intrusion detection performance for attacks with limited training data, making it a promising avenue for bolstering the cybersecurity posture of organizations in an increasingly interconnected and vulnerable digital landscape.

cs.CR↗

arXiv2024

Exploring Emerging Trends in 5G Malicious Traffic Analysis and Incremental Learning Intrusion Detection Strategies

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 of malicious traffic activity on 5G networks. Malicious traffic activity in 5G networks not only has the potential to disrupt communication services, but also to compromise sensitive data. This can have serious consequences for individuals and organizations. In this paper, we first provide an in-depth study of 5G technology and 5G security. Next we analyze and discuss the latest malicious traffic detection under AI and their applicability to 5G networks, and compare the various traffic detection aspects addressed by SOTA. The SOTA in 5G traffic detection is also analyzed. Next, we propose seven criteria for traffic monitoring datasets to confirm their suitability for future traffic detection studies. Finally, we present three major issues that need to be addressed for traffic detection in 5G environment. The concept of incremental learning techniques is proposed and applied in the experiments, and the experimental results prove to be able to solve the three problems to some extent.

cs.CR↗

arXiv2022

A Hybrid Deep Learning Anomaly Detection Framework for Intrusion Detection

Cyber intrusion attacks that compromise the users' critical and sensitive data are escalating in volume and intensity, especially with the growing connections between our daily life and the Internet. The large volume and high complexity of such intrusion attacks have impeded the effectiveness of most traditional defence techniques. While at the same time, the remarkable performance of the machine learning methods, especially deep learning, in computer vision, had garnered research interests from the cyber security community to further enhance and automate intrusion detections. However, the expensive data labeling and limitation of anomalous data make it challenging to train an intrusion detector in a fully supervised manner. Therefore, intrusion detection based on unsupervised anomaly detection is an important feature too. In this paper, we propose a three-stage deep learning anomaly detection based network intrusion attack detection framework. The framework comprises an integration of unsupervised (K-means clustering), semi-supervised (GANomaly) and supervised learning (CNN) algorithms. We then evaluated and showed the performance of our implemented framework on three benchmark datasets: NSL-KDD, CIC-IDS2018, and TON_IoT.

cs.CR↗

arXiv2022

Clustering based opcode graph generation for malware variant detection

Malwares are the key means leveraged by threat actors in the cyber space for their attacks. There is a large array of commercial solutions in the market and significant scientific research to tackle the challenge of the detection and defense against malwares. At the same time, attackers also advance their capabilities in creating polymorphic and metamorphic malwares to make it increasingly challenging for existing solutions. To tackle this issue, we propose a methodology to perform malware detection and family attribution. The proposed methodology first performs the extraction of opcodes from malwares in each family and constructs their respective opcode graphs. We explore the use of clustering algorithms on the opcode graphs to detect clusters of malwares within the same malware family. Such clusters can be seen as belonging to different sub-family groups. Opcode graph signatures are built from each detected cluster. Hence, for each malware family, a group of signatures is generated to represent the family. These signatures are used to classify an unknown sample as benign or belonging to one the malware families. We evaluate our methodology by performing experiments on a dataset consisting of both benign files and malware samples belonging to a number of different malware families and comparing the results to existing approach.

cs.CR↗

arXiv2022

Intrusion Detection in Internet of Things using Convolutional Neural Networks

Internet of Things (IoT) has become a popular paradigm to fulfil needs of the industry such as asset tracking, resource monitoring and automation. As security mechanisms are often neglected during the deployment of IoT devices, they are more easily attacked by complicated and large volume intrusion attacks using advanced techniques. Artificial Intelligence (AI) has been used by the cyber security community in the past decade to automatically identify such attacks. However, deep learning methods have yet to be extensively explored for Intrusion Detection Systems (IDS) specifically for IoT. Most recent works are based on time sequential models like LSTM and there is short of research in CNNs as they are not naturally suited for this problem. In this article, we propose a novel solution to the intrusion attacks against IoT devices using CNNs. The data is encoded as the convolutional operations to capture the patterns from the sensors data along time that are useful for attacks detection by CNNs. The proposed method is integrated with two classical CNNs: ResNet and EfficientNet, where the detection performance is evaluated. The experimental results show significant improvement in both true positive rate and false positive rate compared to the baseline using LSTM.

cs.CR↗