Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples
In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been found to be vulnerable to adversarial examples. Adversarial examples are slightly modified inputs that are intentionally designed to cause a misclassification by the model. In the domains of images and speech, the modifications are so small that they are not seen or heard by humans, but nevertheless greatly affect the classification of the model. Deep learning models have been successfully applied to malware detection. In this domain, generating adversarial examples is not straightforward, as small modifications to the bytes of the file could lead to significant changes in its functionality and validity. We introduce a novel loss function for generating adversarial examples specifically tailored for discrete input sets, such as executable bytes. We modify malicious binaries so that they would be detected as benign, while preserving their original functionality, by injecting a small sequence of bytes (payload) in the binary file. We applied this approach to an end-to-end convolutional deep learning malware detection model and show a high rate of detection evasion. Moreover, we show that our generated payload is robust enough to be transferable within different locations of the same file and across different files, and that its entropy is low and similar to that of benign data sections.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningImage SegmentationMalware DetectionPose EstimationSemantic Segmentationspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach
Deep Learning (DL)-based malware detectors are increasingly adopted for early detection of malicious behavior in cybersecurity. However, their sensitivity to adversarial malware variants has raised immense security conce…
Language ModelingLanguage ModellingTowards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothing
Malware detectors based on deep learning (DL) have been shown to be susceptible to malware examples that have been deliberately manipulated in order to evade detection, a.k.a. adversarial malware examples. More specifica…
Deep LearningBinary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model
Anti-malware engines are the first line of defense against malicious software. While widely used, feature engineering-based anti-malware engines are vulnerable to unseen (zero-day) attacks. Recently, deep learning-based …
Deep LearningFeature EngineeringLanguage ModelingLanguage Modelling+1On the Robustness of Malware Detectors to Adversarial Samples
Adversarial examples add imperceptible alterations to inputs with the objective to induce misclassification in machine learning models. They have been demonstrated to pose significant challenges in domains like image cla…
image-classificationImage ClassificationMalware AnalysisAdversarial Robustness of Deep Learning-Based Malware Detectors via (De)Randomized Smoothing
Deep learning-based malware detectors have been shown to be susceptible to adversarial malware examples, i.e. malware examples that have been deliberately manipulated in order to avoid detection. In light of the vulnerab…
Adversarial Robustness