arXiv subjects

Vrizlynn L. L. Thing

Publications and source records attributed to Vrizlynn L. L. Thing.

At least 19 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

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

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 carry direct financial consequences. This makes them vulnerable to prompt-injection attacks, in which seemingly benign web content conceals adversarial instructions that manipulate the agent's behavior. Existing security benchmarks adopt an \textit{attack-centric} perspective, focusing on the technical feasibility of injections while overlooking the nuanced distribution of resulting harms. In practice, however, prompt-injection risk is victim-dependent: a single exploit can produce asymmetric consequences for different stakeholders, and the same attack pattern may exhibit substantially different effectiveness depending on whom it targets. To capture these properties, we introduce StakeBench, a stakeholder-centric benchmark that systematically categorizes and attributes harm in real-world web agent systems for online shopping. In general, StakeBench decomposes prompt-injection risk into 12 concrete attack objectives across three stakeholder classes, realized by 22 reusable templates and instantiated into 264 executable adversarial cases spanning 12 product categories, with each case evaluated along complementary outcome- and process-level metrics. Evaluating four deployable agent-backbone configurations across 3,168 attacked runs, we find substantial and heterogeneous vulnerabilities: no attack objective is reliably resisted by current LLM-based web agents, and outcomes span four qualitatively distinct modes. These patterns are missed by conventional attack-centric, single-metric evaluation, underscoring the need for stakeholder-aware assessment of LLM-based agents in real-world deployments.

cs.CR↗

arXiv2026

Explaining Intrusion Alert Decisions of Deep Learning-based Network Intrusion Detection Systems for Security Analysts

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 with the domain knowledge of analysts working in Security Operations Center (SOC). We highlight the following features of our framework: (1) a forensic module that isolates the suspect packets/flow which likely caused an alert (2) an explanation module which can handle much more complex feature dependencies in network traffic than existing methods (features can be divided into overlapping groups and some groups are more important than others), and (3) a multi-stage mapping module which translates the feature/group-based explanations generated by explanation module to domain-specific explanations suitable for processing by security analysts. We evaluate EXP-SEC with state-of-the-art DL-based NIDS and our evaluation results show that EXP-SEC outperforms xNIDS (existing best performing explanation framework) in terms of group-level and overlap-aware explanation utility metrics while performing similarly in terms of conventional feature-level metrics such as descriptive accuracy, sparsity and stability. Moreover, taking the case of a state-of-the-art DL-based NIDS, we demonstrate the security analyst-friendly explanation format generated by EXP-SEC.

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

Evaluating The Explainability of State-of-the-Art Deep Learning-based Network Intrusion Detection Systems

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 from hidden correlations? Prior works have applied eXplainable AI (XAI) techniques to ML-based security systems such as conventional ML classifiers trained on public network intrusion datasets, Android malware detection and malicious PDF file detection. However, those works have not evaluated XAI methods on state-of-the-art DL-based NIDSs and do not use latest XAI tools. In this work, we analyze state-of-the-art DL-based NIDS models using conventional as well as recently proposed XAI techniques through extensive experiments with different attack datasets. Furthermore, we introduce a criteria to evaluate the level of agreement between global- and local-level explanations generated for an NIDS. Using this criteria in addition to other security-focused criteria, we compare the explanations generated across XAI methods. The results show that: (1) the decisions of some DL-based NIDS models can be better explained than other models, (2) XAI explanations generated using different tools are in conflict for most of the NIDS models considered in this work and (3) there are significant differences between XAI methods in terms of some security-focused criteria. Based on our results, we make recommendations on how to achieve a balance between explainability and model detection performance.

cs.CR↗

arXiv2025

A Survey of Transaction Tracing Techniques for Blockchain Systems

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 whether the transfer of coins/assets can be tracked within their respective transaction ledger, but also if they can be tracked as they move across ledgers. This is especially important given that there are documented cases of criminals attempting to use these cross-ledger trades to obscure the flow of their coins/assets. In this paper, we perform a systematic review of the various tracing techniques for blockchain transactions proposed in literature, categorize them using multiple criteria (such as tracing approach and targeted objective) and compare them. Based on the above categorization, we provide insights on the state of blockchain transaction tracing literature and identify the limitations of existing approaches. Finally, we suggest directions for future research in this area based on our analysis.

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

CPE-Identifier: Automated CPE identification and CVE summaries annotation with Deep Learning and NLP

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 Platform Enumeration (CPE) with the Common Vulnerabilities and Exposures (CVE) summaries becomes increasingly laborious and slow. The delay causes organisations, which depend on NVD for vulnerability management and security measurement, to be more vulnerable to zero-day attacks. Thus, it is essential to come out with a technique and tool to extract the CPEs in the CVE summaries accurately and quickly. In this work, we propose the CPE-Identifier system, an automated CPE annotating and extracting system, from the CVE summaries. The system can be used as a tool to identify CPE entities from new CVE text inputs. Moreover, we also automate the data generating and labeling processes using deep learning models. Due to the complexity of the CVE texts, new technical terminologies appear frequently. To identify novel words in future CVE texts, we apply Natural Language Processing (NLP) Named Entity Recognition (NER), to identify new technical jargons in the text. Our proposed model achieves an F1 score of 95.48%, an accuracy score of 99.13%, a precision of 94.83%, and a recall of 96.14%. We show that it outperforms prior works on automated CVE-CPE labeling by more than 9% on all metrics.

cs.CR↗

arXiv2024

Privacy-Preserving Intrusion Detection using Convolutional Neural Networks

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 importance of the privacy preservation is fuelled by legal obligations and intellectual property concerns. We explore the use case of a model owner providing an analytic service on customer's private data. No information about the data shall be revealed to the analyst and no information about the model shall be leaked to the customer. Current methods involve costs: accuracy deterioration and computational complexity. The complexity, in turn, results in a longer processing time, increased requirement on computing resources, and involves data communication between the client and the server. In order to deploy such service architecture, we need to evaluate the optimal setting that fits the constraints. And that is what this paper addresses. In this work, we enhance an attack detection system based on Convolutional Neural Networks with privacy-preserving technology based on PriMIA framework that is initially designed for medical data.

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↗