EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
Not on the map. Why?
Abstract (arXiv)
This paper describes EMBER: a labeled benchmark dataset for training machine learning models to statically detect malicious Windows portable executable files. The dataset includes features extracted from 1.1M binary files: 900K training samples (300K malicious, 300K benign, 300K unlabeled) and 200K test samples (100K malicious, 100K benign). To accompany the dataset, we also release open source code for extracting features from additional binaries so that additional sample features can be appended to the dataset. This dataset fills a void in the information security machine learning community: a benign/malicious dataset that is large, open and general enough to cover several interesting use cases. We enumerate several use cases that we considered when structuring the dataset. Additionally, we demonstrate one use case wherein we compare a baseline gradient boosted decision tree model trained using LightGBM with default settings to MalConv, a recently published end-to-end (featureless) deep learning model for malware detection. Results show that even without hyper-parameter optimization, the baseline EMBER model outperforms MalConv. The authors hope that the dataset, code and baseline model provided by EMBER will help invigorate machine learning research for malware detection, in much the same way that benchmark datasets have advanced computer vision research.
Key facts. Cited by 165 papers in the map (data through 13 Oct 2026). First posted on arXiv 12 Apr 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 21; 2022: 26; 2023: 28; 2024: 27; 2025: 35; 2026: 28.
165 papers.
Sort:
By area:
- 2021Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networkscited by 40
- 2022Towards A Proactive ML Approach for Detecting Backdoor Poison Samplescited by 40
- 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgottencited by 25
- 2022BagFlip: A Certified Defense against Data Poisoningcited by 19
- 2021Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Artcited by 18
- 2025EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifierscited by 18
- 2021Adversarial Robustness with Non-uniform Perturbationscited by 17
- 2021MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labelscited by 17
- 2021A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labelscited by 16
- 2022Out of Distribution Data Detection Using Dropout Bayesian Neural Networkscited by 15
- 2022SoK: The Impact of Unlabelled Data in Cyberthreat Detectioncited by 15
- 2023CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenariocited by 15
38 more
- 2025Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineeringcited by 15
- 2022Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifierscited by 14
- 2023Recasting Self-Attention with Holographic Reduced Representationscited by 14
- 2022On the Limitations of Continual Learning for Malware Classificationcited by 12
- 2023Decoding the Secrets of Machine Learning in Malware Classification: A Deep Dive into Datasets, Feature Extraction, and Model Performancecited by 12
- 2023FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysiscited by 12
- 2024Assemblage: Automatic Binary Dataset Construction for Machine Learningcited by 12
- 2021Leveraging Uncertainty for Improved Static Malware Detection Under Extreme False Positive Constraintscited by 11
- 2022MERLIN -- Malware Evasion with Reinforcement LearnINgcited by 11
- 2022XRand: Differentially Private Defense against Explanation-Guided Attackscited by 11
- 2023MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognitioncited by 10
- 2021Malware Analysis with Artificial Intelligence and a Particular Attention on Results Interpretabilitycited by 9
- 2022Quo Vadis: Hybrid Machine Learning Meta-Model based on Contextual and Behavioral Malware Representationscited by 9
- 2024TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time (Extended Version)cited by 9
- 2021Adversarial Transfer Attacks With Unknown Data and Class Overlapcited by 8
- 2024MORPH: Towards Automated Concept Drift Adaptation for Malware Detectioncited by 8
- 2025MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classificationcited by 8
- 2021MalPhase: Fine-Grained Malware Detection Using Network Flow Datacited by 7
- 2021Mate! Are You Really Aware? An Explainability-Guided Testing Framework for Robustness of Malware Detectorscited by 7
- 2022AI-based Malware and Ransomware Detection Modelscited by 7
- 2022AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labelscited by 7
- 2021Towards an Automated Pipeline for Detecting and Classifying Malware through Machine Learningcited by 6
- 2021Explanation-Guided Diagnosis of Machine Learning Evasion Attackscited by 6
- 2022Efficient Malware Analysis Using Metric Embeddingscited by 6
- 2022Transformers for End-to-End InfoSec Tasks: A Feasibility Studycited by 6
- 2023EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysiscited by 6
- 2024Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detectioncited by 6
- 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
- 2025LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysiscited by 6
- 2021Malware Detection Using Frequency Domain-Based Image Visualization and Deep Learningcited by 5
- 2021Realizable Universal Adversarial Perturbations for Malwarecited by 5
- 2021Virus-MNIST: A Benchmark Malware Datasetcited by 5
- 2023PECAN: A Deterministic Certified Defense Against Backdoor Attackscited by 5
- 2023AVScan2Vec: Feature Learning on Antivirus Scan Data for Production-Scale Malware Corporacited by 5
- 2023Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothingcited by 5
- 2023A Comparison of Adversarial Learning Techniques for Malware Detectioncited by 5
- 2024Assessing the Impact of Packing on Machine Learning-Based Malware Detection and Classification Systemscited by 5
- 2026MalSkills: Detecting Malicious Skills in the Agentic Supply Chain via Neuro-symbolic Reasoningcited by 5
50 most cited of 165 All 165 (JSON)
- 2026Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection21 Sep 2026
- 2026Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling17 Sep 2026
- 2026ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers17 Sep 2026
- 2026Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning3 Aug 2026
- 2026Guarding Organizations Against Malware Risk: A Novel Graph-Based Malware Detection Method29 Jul 2026
- 2026Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations27 Jul 2026
- 2026EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability27 Jul 2026
- 2026Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes1 Jul 2026
- 2026MalTree: Tracing Malware Evolution from Embeddings at Scale4 Jun 2026
- 2026Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluation25 May 2026
- 2026SEED: Semi-supervised Continual MalwarE Detection for Tackling ConcEpt Drift on a BuDget24 May 2026
- 2026ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage20 May 2026
38 more
- 2026FreeMOCA: Memory-Free Continual Learning for Malicious Code Analysis10 May 2026
- 2026Quantifiable Uncertainty: A Stochastic Consensus Multi-Agent RAG Framework for Robust Malware Detection8 May 2026
- 2026Beyond the Wrapper: Identifying Artifact Reliance in Static Malware Classifiers using TRUSTEE7 May 2026
- 2026LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution7 May 2026
- 2026Trident: Improving Malware Detection with LLMs and Behavioral Features30 Apr 2026
- 2026Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective24 Apr 2026
- 2026Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks22 Apr 2026
- 2026Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Models2 Apr 2026
- 2026Label-efficient Training Updates for Malware Detection over Time30 Mar 2026
- 2026MalSkills: Detecting Malicious Skills in the Agentic Supply Chain via Neuro-symbolic Reasoning28 Mar 2026
- 2026Machine Learning Transferability for Malware Detection27 Mar 2026
- 2026Detecting Cybersecurity Threats by Integrating Explainable AI with SHAP Interpretability and Strategic Data Sampling22 Feb 2026
- 2026A Unified Evaluation of Learning-Based Similarity Techniques for Malware Detection17 Feb 2026
- 2026LLM-FS: Zero-Shot Feature Selection for Effective and Interpretable Malware Detection10 Feb 2026
- 2026Multimodal Multi-Agent Ransomware Analysis Using AutoGen28 Jan 2026
- 2026FARM: Few-shot Adaptive Malware Family Classification under Concept Drift25 Jan 2026
- 2025MeLeMaD: Adaptive Malware Detection via Chunk-wise Feature Selection and Meta-Learning30 Dec 2025
- 2025Enhancing Decision-Making in Windows PE Malware Classification During Dataset Shifts with Uncertainty Estimation20 Dec 2025
- 2025Clustering Malware at Scale: A First Full-Benchmark Study28 Nov 2025
- 2025Binary-30K: A Heterogeneous Dataset for Deep Learning in Binary Analysis and Malware Detection27 Nov 2025
- 2025Accuracy and Efficiency Trade-Offs in LLM-Based Malware Detection and Explanation: A Comparative Study of Parameter Tuning vs. Full Fine-Tuning24 Nov 2025
- 2025AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research17 Nov 2025
- 2025Efficient Adversarial Malware Defense via Trust-Based Raw Override and Confidence-Adaptive Bit-Depth Reduction16 Nov 2025
- 2025Binary BPE: A Family of Cross-Platform Tokenizers for Binary Analysis14 Nov 2025
- 2025Federated Cyber Defense: Privacy-Preserving Ransomware Detection Across Distributed Systems3 Nov 2025
- 2025DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis30 Sep 2025
- 2025Signal-Based Malware Classification Using 1D CNNs8 Sep 2025
- 2025Cross-Domain Malware Detection via Probability-Level Fusion of Lightweight Gradient Boosting Models30 Aug 2025
- 2025Towards Quantum Machine Learning for Malicious Code Analysis26 Aug 2025
- 2025Demystifying the Role of Rule-based Detection in AI Systems for Windows Malware Detection13 Aug 2025
- 2025Certifiably robust malware detectors by design10 Aug 2025
- 2025Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark8 Aug 2025
- 2025MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning15 Jul 2025
- 2025ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection11 Jul 2025
- 2025Adaptive Malware Detection using Sequential Feature Selection: A Dueling Double Deep Q-Network (D3QN) Framework for Intelligent Classification6 Jul 2025
- 2025RawMal-TF: Raw Malware Dataset Labeled by Type and Family30 Jun 2025
- 2025Efficient Malware Detection with Optimized Learning on High-Dimensional Features18 Jun 2025
- 2025Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Review18 Jun 2025
50 newest of 165 All 165 (JSON)
- 2022Towards A Proactive ML Approach for Detecting Backdoor Poison Samplescited by 40
- 2021Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Artcited by 18
- 2025EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifierscited by 18
- 2021Adversarial Robustness with Non-uniform Perturbationscited by 17
- 2021MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labelscited by 17
- 2021A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labelscited by 16
- 2022Out of Distribution Data Detection Using Dropout Bayesian Neural Networkscited by 15
- 2022SoK: The Impact of Unlabelled Data in Cyberthreat Detectioncited by 15
- 2023CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenariocited by 15
- 2025Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineeringcited by 15
- 2022Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifierscited by 14
- 2023Recasting Self-Attention with Holographic Reduced Representationscited by 14
12 most cited of 160 All 160 (JSON)
- 2026Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection21 Sep 2026
- 2026Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling17 Sep 2026
- 2026ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers17 Sep 2026
- 2026Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning3 Aug 2026
- 2026Guarding Organizations Against Malware Risk: A Novel Graph-Based Malware Detection Method29 Jul 2026
- 2026Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations27 Jul 2026
- 2026EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability27 Jul 2026
- 2026Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes1 Jul 2026
- 2026MalTree: Tracing Malware Evolution from Embeddings at Scale4 Jun 2026
- 2026Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluation25 May 2026
- 2026SEED: Semi-supervised Continual MalwarE Detection for Tackling ConcEpt Drift on a BuDget24 May 2026
- 2026ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage20 May 2026
12 newest of 160 All 160 (JSON)