CyberSec Research

This work addresses the challenge of malware classification using machine learning by developing a novel dataset labeled at both the malware type and family levels. Raw binaries were collected from sources such as VirusShare, VX Underground, and MalwareBazaar, and subsequently labeled with family information parsed from binary names and type-level labels integrated from ClarAVy. The dataset includes 14 malware types and 17 malware families, and was processed using a unified feature extraction pipeline based on static analysis, particularly extracting features from Portable Executable headers, to support advanced classification tasks. The evaluation was focused on three key classification tasks. In the binary classification of malware versus benign samples, Random Forest and XGBoost achieved high accuracy on the full datasets, reaching 98.5% for type-based detection and 98.98% for family-based detection. When using truncated datasets of 1,000 samples to assess performance under limited data conditions, both models still performed strongly, achieving 97.6% for type-based detection and 98.66% for family-based detection. For interclass classification, which distinguishes between malware types or families, the models reached up to 97.5% accuracy on type-level tasks and up to 93.7% on family-level tasks. In the multiclass classification setting, which assigns samples to the correct type or family, SVM achieved 81.1% accuracy on type labels, while Random Forest and XGBoost reached approximately 73.4% on family labels. The results highlight practical trade-offs between accuracy and computational cost, and demonstrate that labeling at both the type and family levels enables more fine-grained and insightful malware classification. The work establishes a robust foundation for future research on advanced malware detection and classification.

Several recent works focused on the best practices for applying machine learning to cybersecurity. In the context of malware, TESSERACT highlighted the impact of concept drift on detection performance and suggested temporal and spatial constraints to be enforced to ensure realistic time-aware evaluations, which have been adopted by the community. In this paper, we demonstrate striking discrepancies in the performance of learning-based malware detection across the same time frame when evaluated on two representative Android malware datasets used in top-tier security conferences, both adhering to established sampling and evaluation guidelines. This questions our ability to understand how current state-of-the-art approaches would perform in realistic scenarios. To address this, we identify five novel temporal and spatial bias factors that affect realistic evaluations. We thoroughly evaluate the impact of these factors in the Android malware domain on two representative datasets and five Android malware classifiers used or proposed in top-tier security conferences. For each factor, we provide practical and actionable recommendations that the community should integrate in their methodology for more realistic and reproducible settings.

Mixed Boolean-Arithmetic (MBA) obfuscation protects intellectual property by converting programs into forms that are more complex to analyze. However, MBA has been increasingly exploited by malware developers to evade detection and cause significant real-world problems. Traditional MBA deobfuscation methods often consider these expressions as part of a black box and overlook their internal semantic information. To bridge this gap, we propose a truth table, which is an automatically constructed semantic representation of an expression's behavior that does not rely on external resources. The truth table is a mathematical form that represents the output of expression for all possible combinations of input. We also propose a general and extensible guided MBA deobfuscation framework (gMBA) that modifies a Transformer-based neural encoder-decoder Seq2Seq architecture to incorporate this semantic guidance. Experimental results and in-depth analysis show that integrating expression semantics significantly improves performance and highlights the importance of internal semantic expressions in recovering obfuscated code to its original form.

Malware detection in Android systems requires both cybersecurity expertise and machine learning (ML) techniques. Automated Machine Learning (AutoML) has emerged as an approach to simplify ML development by reducing the need for specialized knowledge. However, current AutoML solutions typically operate as black-box systems with limited transparency, interpretability, and experiment traceability. To address these limitations, we present MH-AutoML, a domain-specific framework for Android malware detection. MH-AutoML automates the entire ML pipeline, including data preprocessing, feature engineering, algorithm selection, and hyperparameter tuning. The framework incorporates capabilities for interpretability, debugging, and experiment tracking that are often missing in general-purpose solutions. In this study, we compare MH-AutoML against seven established AutoML frameworks: Auto-Sklearn, AutoGluon, TPOT, HyperGBM, Auto-PyTorch, LightAutoML, and MLJAR. Results show that MH-AutoML achieves better recall rates while providing more transparency and control. The framework maintains computational efficiency comparable to other solutions, making it suitable for cybersecurity applications where both performance and explainability matter.

The widespread use of Android applications has made them a prime target for cyberattacks, significantly increasing the risk of malware that threatens user privacy, security, and device functionality. Effective malware detection is thus critical, with static analysis, dynamic analysis, and Machine Learning being widely used approaches. In this work, we focus on a Machine Learning-based method utilizing static features. We first compiled a dataset of benign and malicious APKs and performed static analysis to extract features such as code structure, permissions, and manifest file content, without executing the apps. Instead of relying solely on raw static features, our system uses an LLM to generate high-level functional descriptions of APKs. To mitigate hallucinations, which are a known vulnerability of LLM, we integrated Retrieval-Augmented Generation (RAG), enabling the LLM to ground its output in relevant context. Using carefully designed prompts, we guide the LLM to produce coherent function summaries, which are then analyzed using a transformer-based model, improving detection accuracy over conventional feature-based methods for malware detection.

In the face of evolving cyber threats such as malware, ransomware and phishing, autonomous cybersecurity defense (ACD) systems have become essential for real-time threat detection and response with optional human intervention. However, existing ACD systems rely on limiting assumptions, particularly the stationarity of the underlying network dynamics. In real-world scenarios, network topologies can change due to actions taken by attackers or defenders, system failures, or time evolution of networks, leading to failures in the adaptive capabilities of current defense agents. Moreover, many agents are trained on static environments, resulting in overfitting to specific topologies, which hampers their ability to generalize to out-of-distribution network topologies. This work addresses these challenges by exploring methods for developing agents to learn generalizable policies across dynamic network environments -- general ACD (GACD).

A sophisticated malspam campaign was recently uncovered targeting Latin American countries, with a particular focus on Brazil. This operation utilizes a highly deceptive phishing email to trick users into executing a malicious MSI file, initiating a multi-stage infection. The core of the attack leverages DLL side-loading, where a legitimate executable from Valve Corporation is used to load a trojanized DLL, thereby bypassing standard security defenses. Once active, the malware, a variant of QuasarRAT known as BlotchyQuasar, is capable of a wide range of malicious activities. It is designed to steal sensitive browser-stored credentials and banking information, the latter through fake login windows mimicking well-known Brazilian banks. The threat establishes persistence by modifying the Windows registry , captures user keystrokes through keylogging , and exfiltrates stolen data to a Command-and-Control (C2) server using encrypted payloads. Despite its advanced capabilities, the malware code exhibits signs of rushed development, with inefficiencies and poor error handling that suggest the threat actors prioritized rapid deployment over meticulous design. Nonetheless, the campaign extensive reach and sophisticated mechanisms pose a serious and immediate threat to the targeted regions, underscoring the need for robust cybersecurity defenses.

Deobfuscating JavaScript (JS) code poses a significant challenge in web security, particularly as obfuscation techniques are frequently used to conceal malicious activities within scripts. While Large Language Models (LLMs) have recently shown promise in automating the deobfuscation process, transforming detection and mitigation strategies against these obfuscated threats, a systematic benchmark to quantify their effectiveness and limitations has been notably absent. To address this gap, we present JsDeObsBench, a dedicated benchmark designed to rigorously evaluate the effectiveness of LLMs in the context of JS deobfuscation. We detail our benchmarking methodology, which includes a wide range of obfuscation techniques ranging from basic variable renaming to sophisticated structure transformations, providing a robust framework for assessing LLM performance in real-world scenarios. Our extensive experimental analysis investigates the proficiency of cutting-edge LLMs, e.g., GPT-4o, Mixtral, Llama, and DeepSeek-Coder, revealing superior performance in code simplification despite challenges in maintaining syntax accuracy and execution reliability compared to baseline methods. We further evaluate the deobfuscation of JS malware to exhibit the potential of LLMs in security scenarios. The findings highlight the utility of LLMs in deobfuscation applications and pinpoint crucial areas for further improvement.

The Ethereum Virtual Machine (EVM) is a decentralized computing engine. It enables the Ethereum blockchain to execute smart contracts and decentralized applications (dApps). The increasing adoption of Ethereum sparked the rise of phishing activities. Phishing attacks often target users through deceptive means, e.g., fake websites, wallet scams, or malicious smart contracts, aiming to steal sensitive information or funds. A timely detection of phishing activities in the EVM is therefore crucial to preserve the user trust and network integrity. Some state-of-the art approaches to phishing detection in smart contracts rely on the online analysis of transactions and their traces. However, replaying transactions often exposes sensitive user data and interactions, with several security concerns. In this work, we present PhishingHook, a framework that applies machine learning techniques to detect phishing activities in smart contracts by directly analyzing the contract's bytecode and its constituent opcodes. We evaluate the efficacy of such techniques in identifying malicious patterns, suspicious function calls, or anomalous behaviors within the contract's code itself before it is deployed or interacted with. We experimentally compare 16 techniques, belonging to four main categories (Histogram Similarity Classifiers, Vision Models, Language Models and Vulnerability Detection Models), using 7,000 real-world malware smart contracts. Our results demonstrate the efficiency of PhishingHook in performing phishing classification systems, with about 90% average accuracy among all the models. We support experimental reproducibility, and we release our code and datasets to the research community.

Emerging crypto economies still hemorrhage digital assets because legacy wallets leak private keys at almost every layer of the software stack, from user-space libraries to kernel memory dumps. This paper solves that twin crisis of security and interoperability by re-imagining key management as a platform-level service anchored in ARM TrustZone through OP-TEE. Our architecture fractures the traditional monolithic Trusted Application into per-chain modules housed in a multi-tenant TA store, finally breaking OP-TEE's single-binary ceiling. A cryptographically sealed firmware-over-the-air pipeline welds each TA set to an Android system image, enabling hot-swap updates while Verified Boot enforces rollback protection. Every package carries a chained signature developer first, registry second so even a compromised supply chain cannot smuggle malicious code past the Secure World's RSA-PSS gatekeeper. Inside the TEE, strict inter-TA isolation, cache partitioning, and GP-compliant crypto APIs ensure secrets never bleed across trust boundaries or timing domains. The Rich Execution Environment can interact only via hardware-mediated Secure Monitor Calls, collapsing the surface exposed to malware in Android space. End-users enjoy a single polished interface yet can install or retire Bitcoin, Ethereum, Solana, or tomorrow's chain with one tap, shrinking both storage footprint and audit scope. For auditors, the composition model slashes duplicated verification effort by quarantining blockchain logic inside narrowly scoped modules that share formally specified interfaces. Our threat analysis spans six adversary layers and shows how the design neutralizes REE malware sniffing, OTA injection, and cross-module side channels without exotic hardware. A reference implementation on AOSP exports a Wallet Manager HAL, custom SELinux domains, and a CI/CD pipeline that vet community modules before release. The result is not merely another hardware wallet but a programmable substrate that can evolve at the velocity of the blockchain ecosystem. By welding radical extensibility to hardware-anchored assurance, the platform closes the security-usability gap that has long stymied mass-market self-custody. We posit that modular TEEs are the missing OS primitive for Web3, much as virtual memory unlocked multi-tasking in classical computing. Together, these contributions sketch a blueprint for multi-chain asset management that is auditable, resilient, and poised for global deployment.

Malicious PDF files have emerged as a persistent threat and become a popular attack vector in web-based attacks. While machine learning-based PDF malware classifiers have shown promise, these classifiers are often susceptible to adversarial attacks, undermining their reliability. To address this issue, recent studies have aimed to enhance the robustness of PDF classifiers. Despite these efforts, the feature engineering underlying these studies remains outdated. Consequently, even with the application of cutting-edge machine learning techniques, these approaches fail to fundamentally resolve the issue of feature instability. To tackle this, we propose a novel approach for PDF feature extraction and PDF malware detection. We introduce the PDFObj IR (PDF Object Intermediate Representation), an assembly-like language framework for PDF objects, from which we extract semantic features using a pretrained language model. Additionally, we construct an Object Reference Graph to capture structural features, drawing inspiration from program analysis. This dual approach enables us to analyze and detect PDF malware based on both semantic and structural features. Experimental results demonstrate that our proposed classifier achieves strong adversarial robustness while maintaining an exceptionally low false positive rate of only 0.07% on baseline dataset compared to state-of-the-art PDF malware classifiers.

This paper investigates the application of natural language processing (NLP)-based n-gram analysis and machine learning techniques to enhance malware classification. We explore how NLP can be used to extract and analyze textual features from malware samples through n-grams, contiguous string or API call sequences. This approach effectively captures distinctive linguistic patterns among malware and benign families, enabling finer-grained classification. We delve into n-gram size selection, feature representation, and classification algorithms. While evaluating our proposed method on real-world malware samples, we observe significantly improved accuracy compared to the traditional methods. By implementing our n-gram approach, we achieved an accuracy of 99.02% across various machine learning algorithms by using hybrid feature selection technique to address high dimensionality. Hybrid feature selection technique reduces the feature set to only 1.6% of the original features.

Malware detection using machine learning requires feature extraction from binary files, as models cannot process raw binaries directly. A common approach involves using LIEF for raw feature extraction and the EMBER vectorizer to generate 2381-dimensional feature vectors. However, the high dimensionality of these features introduces significant computational challenges. This study addresses these challenges by applying two dimensionality reduction techniques: XGBoost-based feature selection and Principal Component Analysis (PCA). We evaluate three reduced feature dimensions (128, 256, and 384), which correspond to approximately 5.4%, 10.8%, and 16.1% of the original 2381 features, across four models-XGBoost, LightGBM, Extra Trees, and Random Forest-using a unified training, validation, and testing split formed from the EMBER-2018, ERMDS, and BODMAS datasets. This approach ensures generalization and avoids dataset bias. Experimental results show that LightGBM trained on the 384-dimensional feature set after XGBoost feature selection achieves the highest accuracy of 97.52% on the unified dataset, providing an optimal balance between computational efficiency and detection performance. The best model, trained in 61 minutes using 30 GB of RAM and 19.5 GB of disk space, generalizes effectively to completely unseen datasets, maintaining 95.31% accuracy on TRITIUM and 93.98% accuracy on INFERNO. These findings present a scalable, compute-efficient approach for malware detection without compromising accuracy.

In a context of malware analysis, numerous approaches rely on Artificial Intelligence to handle a large volume of data. However, these techniques focus on data view (images, sequences) and not on an expert's view. Noticing this issue, we propose a preprocessing that focuses on expert knowledge to improve malware semantic analysis and result interpretability. We propose a new preprocessing method which creates JSON reports for Portable Executable files. These reports gather features from both static and behavioral analysis, and incorporate packer signature detection, MITRE ATT\&CK and Malware Behavior Catalog (MBC) knowledge. The purpose of this preprocessing is to gather a semantic representation of binary files, understandable by malware analysts, and that can enhance AI models' explainability for malicious files analysis. Using this preprocessing to train a Large Language Model for Malware classification, we achieve a weighted-average F1-score of 0.94 on a complex dataset, representative of market reality.

Binary code similarity analysis (BCSA) is a crucial research area in many fields such as cybersecurity. Specifically, function-level diffing tools are the most widely used in BCSA: they perform function matching one by one for evaluating the similarity between binary programs. However, such methods need a high time complexity, making them unscalable in large-scale scenarios (e.g., 1/n-to-n search). Towards effective and efficient program-level BCSA, we propose KEENHash, a novel hashing approach that hashes binaries into program-level representations through large language model (LLM)-generated function embeddings. KEENHash condenses a binary into one compact and fixed-length program embedding using K-Means and Feature Hashing, allowing us to do effective and efficient large-scale program-level BCSA, surpassing the previous state-of-the-art methods. The experimental results show that KEENHash is at least 215 times faster than the state-of-the-art function matching tools while maintaining effectiveness. Furthermore, in a large-scale scenario with 5.3 billion similarity evaluations, KEENHash takes only 395.83 seconds while these tools will cost at least 56 days. We also evaluate KEENHash on the program clone search of large-scale BCSA across extensive datasets in 202,305 binaries. Compared with 4 state-of-the-art methods, KEENHash outperforms all of them by at least 23.16%, and displays remarkable superiority over them in the large-scale BCSA security scenario of malware detection.

Effective attribution of Advanced Persistent Threats (APTs) increasingly hinges on the ability to correlate behavioral patterns and reason over complex, varied threat intelligence artifacts. We present AURA (Attribution Using Retrieval-Augmented Agents), a multi-agent, knowledge-enhanced framework for automated and interpretable APT attribution. AURA ingests diverse threat data including Tactics, Techniques, and Procedures (TTPs), Indicators of Compromise (IoCs), malware details, adversarial tools, and temporal information, which are processed through a network of collaborative agents. These agents are designed for intelligent query rewriting, context-enriched retrieval from structured threat knowledge bases, and natural language justification of attribution decisions. By combining Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs), AURA enables contextual linking of threat behaviors to known APT groups and supports traceable reasoning across multiple attack phases. Experiments on recent APT campaigns demonstrate AURA's high attribution consistency, expert-aligned justifications, and scalability. This work establishes AURA as a promising direction for advancing transparent, data-driven, and scalable threat attribution using multi-agent intelligence.

End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain knowledge. While previous work highlighted that deep networks mainly focus on metadata, none investigated the phenomenon further, without quantifying their impact on the decision. In this work, we deepen our understanding of how spurious correlation affects deep learning for malware detection by highlighting how much models rely on empty spaces left by the compiler, which diminishes the relevance of the compiled code. Through our seminal analysis on a small-scale balanced dataset, we introduce a ranking of two end-to-end models to better understand which is more suitable to be put in production.

Large Language Models (LLMs) and generative AI (GenAI) systems such as ChatGPT, Claude, Gemini, LLaMA, and Copilot, developed by OpenAI, Anthropic, Google, Meta, and Microsoft are reshaping digital platforms and app ecosystems while introducing key challenges in cybersecurity, privacy, and platform integrity. Our analysis shows alarming trends: LLM-assisted malware is projected to rise from 2% in 2021 to 50% by 2025; AI-generated Google reviews grew from 1.2% in 2021 to 12.21% in 2023, with an expected 30% by 2025; AI scam reports surged 456%; and misinformation sites increased over 1500%, with a 50-60% increase in deepfakes in 2024. Concurrently, as LLMs have facilitated code development, mobile app submissions grew from 1.8 million in 2020 to 3.0 million in 2024, with 3.6 million expected by 2025. To address AI threats, platforms from app stores like Google Play and Apple to developer hubs like GitHub Copilot, and social platforms like TikTok and Facebook, to marketplaces like Amazon are deploying AI and LLM-based defenses. This highlights the dual nature of these technologies as both the source of new threats and the essential tool for their mitigation. Integrating LLMs into clinical diagnostics also raises concerns about accuracy, bias, and safety, needing strong governance. Drawing on a comprehensive analysis of 455 references, this paper presents a survey of LLM and GenAI risks. We propose a strategic roadmap and operational blueprint integrating policy auditing (CCPA, GDPR), fraud detection, and compliance automation, and an advanced LLM-DA stack with modular components including multi LLM routing, agentic memory, and governance layers to enhance platform integrity. We also provide actionable insights, cross-functional best practices, and real-world case studies. These contributions offer paths to scalable trust, safety, and responsible innovation across digital platforms.