主题为”基于GAN的恶意软件对抗样本生成“。首先介绍了恶意软件发展现状，引出基于模式匹配、特征空间和问题空间三种方式去检测恶意软件。然后介绍了如何生成对抗样本攻击恶意软件检测器，详细介绍了基于GAN的恶意软件对抗样本的MalGAN框架，并对实验结果进行了对比。最后总结了结构性对抗样本的约束：可用转换 、保留语义、似然性、副作用特征。
☆38Jul 25, 2021Updated 4 years ago
Alternatives and similar repositories for MalGAN
Users that are interested in MalGAN are comparing it to the libraries listed below
Sorting:
- A curated resource list of adversarial attacks and defenses for Windows PE malware detection.☆75Sep 2, 2022Updated 3 years ago
- Realization of paper: "Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN" 2017☆130Jul 20, 2018Updated 7 years ago
- 基于深度学习的恶意软件检测研究；MalConv;☆118Jun 22, 2022Updated 3 years ago
- Official Repository of "Robust Malware Classification via Deep Graph Networks on Call Graph Topologies" (ESANN 2021)☆14Jun 16, 2023Updated 2 years ago
- 基于卷积神经网络的恶意软件检测方法☆59May 21, 2019Updated 6 years ago
- We implement MalGAN to attack several PDF classifiers and evaluate the robustness of those models.☆26Jul 4, 2022Updated 3 years ago
- Reproduction of the paper//arxiv.org/pdf/1803.04173.pdf☆19May 21, 2018Updated 7 years ago
- Few-Shot malware classification using fused features of static analysis and dynamic analysis （基于静态+动态分析的混合特征的小样本恶意代码分类框架）☆36Dec 27, 2021Updated 4 years ago
- Defense from the 2020 Microsoft Evasion Competition☆17Apr 27, 2021Updated 4 years ago
- ☆18Apr 4, 2021Updated 4 years ago
- Adversarial Malware Generator Using GANs☆54Jul 25, 2024Updated last year
- Source code of Malware Classification by Learning Semantic and Structural Features of Control Flow Graphs (TrustCom 2021)☆22Mar 17, 2022Updated 3 years ago
- 2021 CCF BDCI 数字安全公开赛“基于人工智能的恶意软件家族分类”赛题第二名Petrichor战队解决方案☆21Jan 24, 2022Updated 4 years ago
- FewShot Malware Classification based on API call sequences, also as code repo for "A Novel Few-Shot Malware Classification Approach for U…☆21Sep 18, 2021Updated 4 years ago
- ☆11Jun 15, 2022Updated 3 years ago
- Android Malware Detection with Graph Convolutional Networks using Function Call Graph and its Derivatives.☆40Aug 2, 2021Updated 4 years ago
- Create adversarial attacks against machine learning Windows malware detectors☆244Nov 27, 2025Updated 3 months ago
- Code for "MalGraph: Hierarchical Graph Neural Networks for Robust Windows Malware Detection"☆48Jan 10, 2022Updated 4 years ago
- Code from the paper: Neurlux: Dynamic Malware Analysis Without Feature Engineering☆14Dec 27, 2020Updated 5 years ago
- the instructions about request access to AdvDroidZero☆13Apr 10, 2024Updated last year
- MAB-Malware an open-source reinforcement learning framework to generate AEs for PE malware. We model this problem as a classic multi-arme…☆54Apr 15, 2025Updated 10 months ago
- ☆28Oct 21, 2020Updated 5 years ago
- ☆32Jul 22, 2022Updated 3 years ago
- ☆14Jul 14, 2019Updated 6 years ago
- 恶意软件家族样本识别/分类器☆13Aug 26, 2021Updated 4 years ago
- adversarial examples, adversarial malware examples, adversarial malware detection, adversarial deep ensemble, Android malware variants☆58Mar 24, 2023Updated 2 years ago
- A Benchmark Dataset for Trustworthy Malware Family Classification under Concept Drift☆16Mar 14, 2025Updated 11 months ago
- ☆38Aug 8, 2024Updated last year
- My replication of the paper "Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN"☆16Apr 27, 2020Updated 5 years ago
- Hybrid Machine Learning Model for Malware Detection based on Windows Kernel Emulation☆41Apr 24, 2023Updated 2 years ago
- [IEEE S&P Workshop 2018] "Adversarial Deep Learning for Robust Detection of Binary Encoded Malware" Abdullah Al-Dujaili, Alex Huang, Erik…☆111Jul 25, 2024Updated last year
- Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detection☆77Oct 8, 2025Updated 4 months ago
- adversarial malware detection via a principled way☆24Apr 27, 2023Updated 2 years ago
- 使用Bert做embedding，结合BiLSTM做恶意软件的多分类任务☆42Nov 18, 2020Updated 5 years ago
- Code for our DLS'21 paper - BODMAS: An Open Dataset for Learning based Temporal Analysis of PE Malware. BODMAS is short for Blue Hexagon …☆91Mar 31, 2024Updated last year
- 本科毕业设计，参考LENET-5模型，将恶意软件转化为灰度图，通过卷积神经网络实现了恶意软件检测分类，准确率达98%。☆26Jul 4, 2020Updated 5 years ago
- Papers, code and datasets about deep learning for Android malware defenses and malware detection☆148Nov 21, 2023Updated 2 years ago
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆60Apr 29, 2022Updated 3 years ago
- Official code for the paper entitled "Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks"☆31Apr 15, 2025Updated 10 months ago