Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN

Abstract

Machine learning has been used to detect new malware in recent years, while malware authors have strong motivation to attack such algorithms. Malware authors usually have no access to the detailed structures and parameters of the machine learning models used by malware detection systems, and therefore they can only perform black-box attacks. This paper proposes a generative adversarial network (GAN) based algorithm named MalGAN to generate adversarial malware examples, which are able to bypass black-box machine learning based detection models. MalGAN uses a substitute detector to fit the black-box malware detection system. A generative network is trained to minimize the generated adversarial examples' malicious probabilities predicted by the substitute detector. The superiority of MalGAN over traditional gradient based adversarial example generation algorithms is that MalGAN is able to decrease the detection rate to nearly zero and make the retraining based defensive method against adversarial examples hard to work.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Improved Techniques for Training GANs
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Adversarial Perturbations Against Deep Neural Networks for Malware Classification
• Practical Black-Box Attacks against Machine Learning
• A General Retraining Framework for Scalable Adversarial Classification

Cited by in corpus (87)

• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• The Space of Transferable Adversarial Examples
• IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Flow-based Network Traffic Generation using Generative Adversarial Networks
• Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
• Generating Adversarial Examples with Adversarial Networks
• Adversarial Examples: Attacks and Defenses for Deep Learning
• Evaluating and Improving Adversarial Robustness of Machine Learning-Based Network Intrusion Detectors
• Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Motivating the Rules of the Game for Adversarial Example Research
• Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
• Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art
• CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning
• Deep Learning for Android Malware Defenses: a Systematic Literature Review
• IoT-based Android Malware Detection Using Graph Neural Network With Adversarial Defense
• Black-Box Attacks against RNN based Malware Detection Algorithms
• Fusing Feature Engineering and Deep Learning: A Case Study for Malware Classification
• Hardening Random Forest Cyber Detectors Against Adversarial Attacks
• EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detection
• Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes
• Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
• Adversarial Examples - A Complete Characterisation of the Phenomenon
• Arms Race in Adversarial Malware Detection: A Survey
• Machine Learning in Cyber-Security - Problems, Challenges and Data Sets
• Machine Learning (In) Security: A Stream of Problems
• Generation & Evaluation of Adversarial Examples for Malware Obfuscation
• Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks
• Creating Valid Adversarial Examples of Malware
• Towards a Robust Deep Neural Network in Texts: A Survey
• The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey
• MaskDGA: A Black-box Evasion Technique Against DGA Classifiers and Adversarial Defenses
• EvilModel 2.0: Bringing Neural Network Models into Malware Attacks
• Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• MAB-Malware: A Reinforcement Learning Framework for Attacking Static Malware Classifiers
• Morphence: Moving Target Defense Against Adversarial Examples
• Towards resilient machine learning for ransomware detection
• Query-Free Evasion Attacks Against Machine Learning-Based Malware Detectors with Generative Adversarial Networks
• MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
• DRLDO: A novel DRL based De-ObfuscationSystem for Defense against Metamorphic Malware
• Android HIV: A Study of Repackaging Malware for Evading Machine-Learning Detection
• Packet-Level Adversarial Network Traffic Crafting using Sequence Generative Adversarial Networks
• Enhancing Robustness of Deep Neural Networks Against Adversarial Malware Samples: Principles, Framework, and AICS'2019 Challenge
• Security and Privacy for Artificial Intelligence: Opportunities and Challenges
• Query-limited Black-box Attacks to Classifiers
• Generating Natural Language Adversarial Examples on a Large Scale with Generative Models
• Generic Black-Box End-to-End Attack Against State of the Art API Call Based Malware Classifiers
• A Comparison of Adversarial Learning Techniques for Malware Detection
• Adapting Novelty towards Generating Antigens for Antivirus systems
• Towards Security Threats of Deep Learning Systems: A Survey
• Adversarial Examples on Object Recognition: A Comprehensive Survey
• Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examples
• Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasets
• Why an Android App is Classified as Malware? Towards Malware Classification Interpretation
• GANG-MAM: GAN based enGine for Modifying Android Malware
• Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Models
• RayS: A Ray Searching Method for Hard-label Adversarial Attack
• On Training Robust PDF Malware Classifiers
• TSS: Transformation-Specific Smoothing for Robustness Certification
• EGAN: Evolutional GAN for Ransomware Evasion
• PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving
• AutoGAN: Robust Classifier Against Adversarial Attacks
• SIGMA : Strengthening IDS with GAN and Metaheuristics Attacks
• Few-Features Attack to Fool Machine Learning Models through Mask-Based GAN
• Omni: Automated Ensemble with Unexpected Models against Adversarial Evasion Attack
• A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
• Brain-inspired reverse adversarial examples
• Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
• Malware Evasion Attack and Defense
• CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations
• Implicit Generative Modeling of Random Noise during Training for Adversarial Robustness
• IWA: Integrated Gradient based White-box Attacks for Fooling Deep Neural Networks
• Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior
• Blackbox Trojanising of Deep Learning Models : Using non-intrusive network structure and binary alterations
• Being Single Has Benefits. Instance Poisoning to Deceive Malware Classifiers
• When the Guard failed the Droid: A case study of Android malware
• Generative Models for Security: Attacks, Defenses, and Opportunities
• Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations
• Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial Nets
• A Review of Computer Vision Methods in Network Security
• Dissecting Malware in the Wild
• A Comparison of State-of-the-Art Techniques for Generating Adversarial Malware Binaries
• A Survey on Threat Situation Awareness Systems: Framework, Techniques, and Insights
• ML-based IoT Malware Detection Under Adversarial Settings: A Systematic Evaluation
• Adversarial Attacks on Cognitive Self-Organizing Networks: The Challenge and the Way Forward