Malware family classification remains a challenging task in automated malware analysis, particularly in real-world settings characterized by obfuscation, packing, and rapidly evolving threats. Existing machine learning and deep learning approaches typically depend on labeled datasets, handcrafted features, supervised training, or dynamic analysis, which limits their scalability and effectiveness in open-world scenarios.
This paper presents a zero-label malware family classification framework based on a weighted hierarchical ensemble of pretrained large language models (LLMs). Rather than relying on feature-level learning or model retraining, the proposed approach aggregates decision-level predictions from multiple LLMs with complementary reasoning strengths. Model outputs are weighted using empirically derived macro-F1 scores and organized hierarchically, first resolving coarse-grained malicious behavior before assigning fine-grained malware families. This structure enhances robustness, reduces individual model instability, and aligns with analyst-style reasoning.
Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
Virelya Intelligence Research Labs（Virelya智能研究实验室）；Google（谷歌）
We propose in this paper a new propagation vector for malicious software by abusing the Tor network. Tor is particularly relevant, since operating a Tor exit node is easy and involves low costs compared to attack institutional or ISP networks. After presenting the Tor network from an attacker perspective, we describe an automated exploitation malware which is operated on a Tor exit node targeting to infect web browsers. Our experiments show that the current deployed Tor network, provides a large amount of potential victims.
In this paper we introduce CrowdSource, a statistical natural language processing system designed to make rapid inferences about malware functionality based on printable character strings extracted from malware binaries. CrowdSource "learns" a mapping between low-level language and high-level software functionality by leveraging millions of web technical documents from StackExchange, a popular network of technical question and answer sites, using this mapping to infer malware capabilities. This paper describes our approach and provides an evaluation of its accuracy and performance, demonstrati…
Centre for Secure Information Technologies (CSIT)（安全信息技术中心（CSIT））；Queen’s University Belfast（贝尔法斯特女王大学）
We propose the Malceiver, a hierarchical Perceiver model for Android malware detection that makes use of multi-modal features. The primary inputs are the opcode sequence and the requested permissions of a given Android APK file. To reach a malware classification decision the model combines hierarchical features extracted from the opcode sequence together with the requested permissions. The model's architecture is based on the Perceiver/PerceiverIO which allows for very long opcode sequences to be processed efficiently. Our proposed model can be easily extended to use multi-modal features. We s…
Perimeter-based detection is no longer sufficient for mitigating the threat posed by malicious software. This is evident as antivirus (AV) products are replaced by endpoint detection and response (EDR) products, the latter allowing visibility into live machine activity rather than relying on the AV to filter out malicious artefacts. This paper argues that detecting malware in real-time on an endpoint necessitates an automated response due to the rapid and destructive nature of some malware. The proposed model uses statistical filtering on top of a machine learning dynamic behavioural malware d…
The popularity of Windows attracts the attention of hackers/cyber-attackers, making Windows devices the primary target of malware attacks in recent years. Several sophisticated malware variants and anti-detection methods have been significantly enhanced and as a result, traditional malware detection techniques have become less effective. This work presents MalBehavD-V1, a new behavioural dataset of Windows Application Programming Interface (API) calls extracted from benign and malware executable files using the dynamic analysis approach. In addition, we present MalDetConV, a new automated beha…
Semi-supervised Classification of Malware Families Under Extreme Class Imbalance via Hierarchical Non-Negative Matrix Factorization with Automatic Model Selection
本文提出一种名为 HNMFk Classifier 的分层半监督算法，基于带自动模型选择的非负矩阵分解，通过支持弃权（不执行）预测，在极端类别不平衡和标注数据稀缺的情况下有效分类恶意软件家族并识别新型家族，在 EMBER-2018 数据集上取得 0.80 的 F1 分数。
This paper proposes a technique for automatically learning semantic malware signatures for Android from very few samples of a malware family. The key idea underlying our technique is to look for a maximally suspicious common subgraph (MSCS) that is shared between all known instances of a malware family. An MSCS describes the shared functionality between multiple Android applications in terms of inter-component call relations and their semantic metadata (e.g., data-flow properties). Our approach identifies such maximally suspicious common subgraphs by reducing the problem to maximum satisfiabil…
The evolution of mobile malware poses a serious threat to smartphone security. Today, sophisticated attackers can adapt by maximally sabotaging machine-learning classifiers via polluting training data, rendering most recent machine learning-based malware detection tools (such as Drebin, DroidAPIMiner, and MaMaDroid) ineffective. In this paper, we explore the feasibility of constructing crafted malware samples; examine how machine-learning classifiers can be misled under three different threat models; then conclude that injecting carefully crafted data into training data can significantly reduc…
Università degli Studi di Torino（都灵大学）；aizoOn Technology Consulting（aizoOn技术咨询公司）
The constant growth in the number of malware - software or code fragment potentially harmful for computers and information networks - and the use of sophisticated evasion and obfuscation techniques have seriously hindered classic signature-based approaches. On the other hand, malware detection systems based on machine learning techniques started offering a promising alternative to standard approaches, drastically reducing analysis time and turning out to be more robust against evasion and obfuscation techniques. In this paper, we propose a malware taxonomic classification pipeline able to clas…
Malware detection is a growing problem particularly on the Android mobile platform due to its increasing popularity and accessibility to numerous third party app markets. This has also been made worse by the increasingly sophisticated detection avoidance techniques employed by emerging malware families. This calls for more effective techniques for detection and classification of Android malware. Hence, in this paper we present an n-opcode analysis based approach that utilizes machine learning to classify and categorize Android malware. This approach enables automated feature discovery that eli…
Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University（北京交通大学智能交通信息安全与隐私保护北京市重点实验室）
Malware is being increasingly threatening and malware detectors based on traditional signature-based analysis are no longer suitable for current malware detection. Recently, the models based on machine learning (ML) are developed for predicting unknown malware variants and saving human strength. However, most of the existing ML models are black-box, which made their pre-diction results undependable, and therefore need further interpretation in order to be effectively deployed in the wild. This paper aims to examine and categorize the existing researches on ML-based malware detector interpretab…
Ransomware, a class of self-propagating malware that uses encryption to hold the victims' data ransom, has emerged in recent years as one of the most dangerous cyber threats, with widespread damage; e.g., zero-day ransomware WannaCry has caused world-wide catastrophe, from knocking U.K. National Health Service hospitals offline to shutting down a Honda Motor Company in Japan[1]. Our close collaboration with security operations of large enterprises reveals that defense against ransomware relies on tedious analysis from high-volume systems logs of the first few infections. Sandbox analysis of fr…
The wide acceptance of Internet of Things (IoT) for both household and industrial applications is accompanied by several security concerns. A major security concern is their probable abuse by adversaries towards their malicious intent. Understanding and analyzing IoT malicious behaviors is crucial, especially with their rapid growth and adoption in wide-range of applications. However, recent studies have shown that machine learning-based approaches are susceptible to adversarial attacks by adding junk codes to the binaries, for example, with an intention to fool those machine learning or deep …
Identifying threats in a network traffic flow which is encrypted is uniquely challenging. On one hand it is extremely difficult to simply decrypt the traffic due to modern encryption algorithms. On the other hand, passing such an encrypted stream through pattern matching algorithms is useless because encryption ensures there aren't any. Moreover, evaluating such models is also difficult due to lack of labeled benign and malware datasets. Other approaches have tried to tackle this problem by employing observable meta-data gathered from the flow. We try to augment this approach by extending it t…
Android malware has been on the rise in recent years due to the increasing popularity of Android and the proliferation of third party application markets. Emerging Android malware families are increasingly adopting sophisticated detection avoidance techniques and this calls for more effective approaches for Android malware detection. Hence, in this paper we present and evaluate an n-gram opcode features based approach that utilizes machine learning to identify and categorize Android malware. This approach enables automated feature discovery without relying on prior expert or domain knowledge f…
The design of attacks for cyber physical systems is critical to assess CPS resilience at design time and run-time, and to generate rich datasets from testbeds for research. Attacks against cyber physical systems distinguish themselves from IT attacks in that the main objective is to harm the physical system. Therefore, both cyber and physical system knowledge are needed to design such attacks. The current practice to generate attacks either focuses on the cyber part of the system using IT cyber security existing body of knowledge, or uses heuristics to inject attacks that could potentially har…
MalVol-25: A Diverse, Labelled and Detailed Volatile Memory Dataset for Malware Detection and Response Testing and Validation
London Metropolitan University（伦敦 Metropolitan 大学）；Cyber Security Research Centre（网络安全研究中心）；Cybersecurity Institute（网络安全研究所）；Department of Computer Science（计算机科学系）
Android is becoming ubiquitous and currently has the largest share of the mobile OS market with billions of application downloads from the official app market. It has also become the platform most targeted by mobile malware that are becoming more sophisticated to evade state-of-the-art detection approaches. Many Android malware families employ obfuscation techniques in order to avoid detection and this may defeat static analysis based approaches. Dynamic analysis on the other hand may be used to overcome this limitation. Hence in this paper we propose DynaLog, a dynamic analysis based framewor…
With malware detection techniques increasingly adopting machine learning approaches, the creation of precise training sets becomes more and more important. Large data sets of realistic web traffic, correctly classified as benign or malicious are needed, not only to train classic and deep learning algorithms, but also to serve as evaluation benchmarks for existing malware detection products. Interestingly, despite the vast number and versatility of threats a user may encounter when browsing the web, actual malicious content is often hard to come by, since prerequisites such as browser and opera…
Security operation centers (SOCs) typically use a variety of tools to collect large volumes of host logs for detection and forensic of intrusions. Our experience, supported by recent user studies on SOC operators, indicates that operators spend ample time (e.g., hundreds of man-hours) on investigations into logs seeking adversarial actions. Similarly, reconfiguration of tools to adapt detectors for future similar attacks is commonplace upon gaining novel insights (e.g., through internal investigation or shared indicators). This paper presents an automated malware pattern-extraction and early d…
Packed Malware Detection Using Grayscale Binary-to-Image Representations
Canadian Institute for Cybersecurity (CIC)（加拿大网络安全研究所）；University of New Brunswick（新不伦瑞克大学）；Behaviour-Centric Cybersecurity Center (BCCC)（以行为为中心的网络安全中心）；York University（约克大学）
Threats from the internet, particularly malicious software (i.e., malware) often use cryptographic algorithms to disguise their actions and even to take control of a victim's system (as in the case of ransomware). Malware and other threats proliferate too quickly for the time-consuming traditional methods of binary analysis to be effective. By automating detection and classification of cryptographic algorithms, we can speed program analysis and more efficiently combat malware. This thesis will present several methods of leveraging machine learning to automatically discover and classify cryptog…
The use of machine learning and intelligent systems has become an established practice in the realm of malware detection and cyber threat prevention. In an environment characterized by widespread accessibility and big data, the feasibility of malware classification without the use of artificial intelligence-based techniques has been diminished exponentially. Also characteristic of the contemporary realm of automated, intelligent malware detection is the threat of adversarial machine learning. Adversaries are looking to target the underlying data and/or algorithm responsible for the functionali…
Malware programs are diverse, with varying objectives, functionalities, and threat levels ranging from mere pop-ups to financial losses. Consequently, their run-time footprints across the system differ, impacting the optimal data source (Network, Operating system (OS), Hardware) and features that are instrumental to malware detection. Further, the variations in threat levels of malware classes affect the user requirements for detection. Thus, the optimal tuple of <data-source, features, user-requirements> is different for each malware class, impacting the state-of-the-art detection solutions t…
As currently classical malware detection methods based on signatures fail to detect new malware, they are not always efficient with new obfuscation techniques. Besides, new malware is easily created and old malware can be recoded to produce new one. Therefore, classical Antivirus becomes consistently less effective in dealing with those new threats. Also malware gets hand tailored to bypass network security and Antivirus. But as analysts do not have enough time to dissect suspected malware by hand, automated approaches have been developed. To cope with the mass of new malware, statistical and …
Microsoft R&D, India（微软研发中心，印度）；BITS Pilani, Goa, India（比拉尼大学果阿分校，印度）
Long-Short-Term-Memory (LSTM) networks have shown great promise in artificial intelligence (AI) based language modeling. Recently, LSTM networks have also become popular for designing AI-based Intrusion Detection Systems (IDS). However, its applicability in IDS is studied largely in the default settings as used in language models. Whereas security applications offer distinct conditions and hence warrant careful consideration while applying such recurrent networks. Therefore, we conducted one of the most exhaustive works on LSTM hyper-parameters for IDS and experimented with approx. 150 LSTM co…
Recent statistics show that in 2015 more than 140 millions new malware samples have been found. Among these, a large portion is due to ransomware, the class of malware whose specific goal is to render the victim's system unusable, in particular by encrypting important files, and then ask the user to pay a ransom to revert the damage. Several ransomware include sophisticated packing techniques, and are hence difficult to statically analyse. We present EldeRan, a machine learning approach for dynamically analysing and classifying ransomware. EldeRan monitors a set of actions performed by applica…
AndroTruth: A Reliable Benchmark Android Malware Dataset Derived from Technical Expert Reports
School of Cyber Security, Tianjin University（天津大学网络安全学院）；School of Cyber Science and Technology, Shihezi University（石河子大学网络空间科学与技术学院）；School of Software, Tiangong University（天津工业大学软件学院）；State Grid Xinjiang Electric Power Research Institute（国网新疆电力有限公司电力科学研究院）
