On Effectiveness of Adversarial Examples and Defenses for Malware Classification

Takabi, Hassan

doi:10.1007/978-3-030-37231-6_22

Cited by 14 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning techniques were not primarily designed to work with cyber security so an evasion can easily fool the ML [608][609][610]. Research is going on to provide a solution by having adversarial training [611][612][613][614][615].…”

Section: ) Techniques and Methodsmentioning

confidence: 99%

A Survey on Machine Learning Techniques for Cyber Security in the Last Decade

et al. 2020

View full text Add to dashboard Cite

Pervasive growth and usage of the Internet and mobile applications have expanded cyberspace. The cyberspace has become more vulnerable to automated and prolonged cyberattacks. Cyber security techniques provide enhancements in security measures to detect and react against cyberattacks. The previously used security systems are no longer sufficient because cybercriminals are smart enough to evade conventional security systems. Conventional security systems lack efficiency in detecting previously unseen and polymorphic security attacks. Machine learning (ML) techniques are playing a vital role in numerous applications of cyber security. However, despite the ongoing success, there are significant challenges in ensuring the trustworthiness of ML systems. There are incentivized malicious adversaries present in the cyberspace that are willing to game and exploit such ML vulnerabilities. This paper aims to provide a comprehensive overview of the challenges that ML techniques face in protecting cyberspace against attacks, by presenting a literature on ML techniques for cyber security including intrusion detection, spam detection, and malware detection on computer networks and mobile networks in the last decade. It also provides brief descriptions of each ML method, frequently used security datasets, essential ML tools, and evaluation metrics to evaluate a classification model. It finally discusses the challenges of using ML techniques in cyber security. This paper provides the latest extensive bibliography and the current trends of ML in cyber security.

show abstract

Section: ) Techniques and Methodsmentioning

confidence: 99%

A Survey on Machine Learning Techniques for Cyber Security in the Last Decade

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Therefore, adversarial learning attacks and protections on deep learning based Android malware analysis attracts considerable attention currently. In collected studies, the researchers investigate the effectiveness of the adversarial attacks against DL-based Android malware analyzers [26,57,78,92], the robustness of defense strategies [156], or both of them [90,128,157].…”

Section: Adversarial Learning Attacks and Protectionsmentioning

confidence: 99%

“…OPEN ISSUE Verifying the existence of certain categorical characteristics of Android applications, such as permissions/API calls by static analysis or certain malicious behaviors by dynamic analysis, is widely used to construct feature vectors [5,7,18,22,29,40,44,45,47,57,67,68,74,78,90,92,101,105,109,111,113,128,131,143,145,156,157,166,170,172,174,179,185,197,198,203,209]. The researchers usually build a look-up table to list all the potential features, based on prior knowledge or feature selection approaches, and a fixed-size binary feature vector is created to represent the feature information for each application.…”

Section: Rq21 How Features Are Processed For Model Training?mentioning

confidence: 99%

“…Podschwadt et al [128] further evaluated the effectiveness of twelve adversarial attack approaches and four defense techniques for DL-based malware detection based on one-hot feature vectors. This work demonstrated that although Adversarial Training performed strongly, most defense approaches adapted from image classification were not efficient in malware detection, which also showed specific defense approaches to Android malware defense models were needed.…”

Section: 38mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Android Malware Defenses: a Systematic Literature Review

Liu,

Tantithamthavorn,

et al. 2021

Preprint

View full text Add to dashboard Cite

Malicious applications (especially in the Android platform) are a serious threat to developers and end-users. Many research efforts have hence been devoted to developing effective approaches to defend Android malware. However, with the explosive growth of Android malware and the continuous advancement of malicious evasion technologies like obfuscation and reflection, android malware defenses based on manual rules or traditional machine learning may not be effective due to limited apriori knowledge. In recent years, a dominant research field of deep learning (DL) with the powerful feature abstraction ability has demonstrated a compelling and promising performance in various fields, like Nature Language processing and image processing. To this end, employing deep learning techniques to thwart the attack of Android malware has recently gained considerable research attention. Yet, there exists no systematic literature review that focuses on deep learning approaches for Android Malware defenses. In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment. As a result, a total of 104 studies were identified over the period 2014-2020. The results of our investigation show that even though most of these studies still mainly consider DL-based on Android malware detection, 35 primary studies (33.7%) design the defenses approaches based on other scenarios. This review also describes research trends, research focuses, challenges, and future research directions in DL-based Android malware defenses.CCS Concepts: • Security and privacy → Malware and its mitigation; Software security engineering;• General and reference → Surveys and overviews.

show abstract

“…DL-based malware detection approaches are susceptible to adversarial attacks [33][34][35][36][37]. Adversarial modifications by manipulating only a small fraction of raw binary data may lead to misclassification.…”

Section: Adversarial Attack Against Malware Detection Modelmentioning

confidence: 99%

Binary Black‐Box Adversarial Attacks with Evolutionary Learning against IoT Malware Detection

Wang

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

5G is about to open Pandora’s box of security threats to the Internet of Things (IoT). Key technologies, such as network function virtualization and edge computing introduced by the 5G network, bring new security threats and risks to the Internet infrastructure. Therefore, higher detection and defense against malware are required. Nowadays, deep learning (DL) is widely used in malware detection. Recently, research has demonstrated that adversarial attacks have posed a hazard to DL-based models. The key issue of enhancing the antiattack performance of malware detection systems that are used to detect adversarial attacks is to generate effective adversarial samples. However, numerous existing methods to generate adversarial samples are manual feature extraction or using white-box models, which makes it not applicable in the actual scenarios. This paper presents an effective binary manipulation-based attack framework, which generates adversarial samples with an evolutionary learning algorithm. The framework chooses some appropriate action sequences to modify malicious samples. Thus, the modified malware can successfully circumvent the detection system. The evolutionary algorithm can adaptively simplify the modification actions and make the adversarial sample more targeted. Our approach can efficiently generate adversarial samples without human intervention. The generated adversarial samples can effectively combat DL-based malware detection models while preserving the consistency of the executable and malicious behavior of the original malware samples. We apply the generated adversarial samples to attack the detection engines of VirusTotal. Experimental results illustrate that the adversarial samples generated by our method reach an evasion success rate of 47.8%, which outperforms other attack methods. By adding adversarial samples in the training process, the MalConv network is retrained. We show that the detection accuracy is improved by 10.3%.

show abstract

On Effectiveness of Adversarial Examples and Defenses for Malware Classification

Cited by 14 publications

References 22 publications

A Survey on Machine Learning Techniques for Cyber Security in the Last Decade

A Survey on Machine Learning Techniques for Cyber Security in the Last Decade

Deep Learning for Android Malware Defenses: a Systematic Literature Review

Binary Black‐Box Adversarial Attacks with Evolutionary Learning against IoT Malware Detection

Contact Info

Product

Resources

About