DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift

• URL: http://arxiv.org/abs/2508.18839v1
• Date: Tue, 26 Aug 2025 09:15:33 GMT
• Title: DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
• Authors: Shae McFadden, Myles Foley, Mario D'Onghia, Chris Hicks, Vasilios Mavroudis, Nicola Paoletti, Fabio Pierazzi,
• Abstract summary: We develop a novel formulation of malware detection as a one-step Markov Decision Process.<n>We train a deep reinforcement learning (DRL) agent, simultaneously optimizing sample classification performance and rejecting high-risk samples for manual labeling.<n>Our results demonstrate for the first time that DRL can facilitate effective malware detection and improved resiliency to concept drift.
• Score: 17.324132213093872
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Malware detection in real-world settings must deal with evolving threats, limited labeling budgets, and uncertain predictions. Traditional classifiers, without additional mechanisms, struggle to maintain performance under concept drift in malware domains, as their supervised learning formulation cannot optimize when to defer decisions to manual labeling and adaptation. Modern malware detection pipelines combine classifiers with monthly active learning (AL) and rejection mechanisms to mitigate the impact of concept drift. In this work, we develop a novel formulation of malware detection as a one-step Markov Decision Process and train a deep reinforcement learning (DRL) agent, simultaneously optimizing sample classification performance and rejecting high-risk samples for manual labeling. We evaluated the joint detection and drift mitigation policy learned by the DRL-based Malware Detection (DRMD) agent through time-aware evaluations on Android malware datasets subject to realistic drift requiring multi-year performance stability. The policies learned under these conditions achieve a higher Area Under Time (AUT) performance compared to standard classification approaches used in the domain, showing improved resilience to concept drift. Specifically, the DRMD agent achieved a $5.18\pm5.44$, $14.49\pm12.86$, and $10.06\pm10.81$ average AUT performance improvement for the classification only, classification with rejection, and classification with rejection and AL settings, respectively. Our results demonstrate for the first time that DRL can facilitate effective malware detection and improved resiliency to concept drift in the dynamic environment of the Android malware domain.

Related papers

• CITADEL: A Semi-Supervised Active Learning Framework for Malware Detection Under Continuous Distribution Drift [2.6040598178524106]
  We propose CITADEL, a robust semi-supervised active learning framework for Android malware detection.<n>We introduce malware-specific augmentations, Bernoulli bit flips and masking, that simulate realistic drift behaviors.<n>We show that CITADEL outperforms prior work, achieving F1 score of over 1%, 3%, 7%, and 14% respectively, using only 40% labeled samples.
  arXiv  Detail & Related papers  (2025-11-15T01:34:15Z)
• EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels [85.78886153628663]
  Open-Set Domain Generalization aims to enable deep learning models to recognize unseen categories in new domains.<n>Label noise hinders open-set domain generalization by corrupting source-domain knowledge.<n>We propose Evidential Reliability-Aware Residual Flow Meta-Learning (EReLiFM) to bridge domain gaps.
  arXiv  Detail & Related papers  (2025-10-14T16:23:11Z)
• ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection [0.8192907805418583]
  Adapting machine learning models to changing data distributions requires frequent updates.<n>We introduce texttADAPT, a novel pseudo-labeling semi-supervised algorithm for addressing concept drift.
  arXiv  Detail & Related papers  (2025-07-11T13:47:07Z)
• EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning [53.88000987041739]
  Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time.<n>We propose the Elastic Knowledge Preservation and Compensation (EKPC) method, integrating Importance-aware importance Regularization (IPR) and Trainable Semantic Drift Compensation (TSDC) for CIL.
  arXiv  Detail & Related papers  (2025-06-14T05:19:58Z)
• Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning [73.40364018029673]
  Continual test-time adaptive object detection (CTTA-OD) aims to online adapt a source pre-trained detector to ever-changing environments.<n>Our motivation stems from the observation that not all learned source features are beneficial.<n>Our method achieves superior adaptation performance while reducing computational overhead by 12% in FLOPs.
  arXiv  Detail & Related papers  (2025-06-03T05:27:56Z)
• Cluster Analysis and Concept Drift Detection in Malware [1.3812010983144798]
  Concept drift refers to gradual or sudden changes in the properties of data that affect the accuracy of machine learning models.<n>We propose and analyze a clustering-based approach to detecting concept drift in the malware domain.
  arXiv  Detail & Related papers  (2025-02-19T22:42:30Z)
• Revisiting Concept Drift in Windows Malware Detection: Adaptation to Real Drifted Malware with Minimal Samples [10.352741619176383]
  We propose a new technique for detecting and classifying drifted malware.<n>It learns drift-invariant features in malware control flow graphs by leveraging graph neural networks with adversarial domain adaptation.<n>Our approach significantly improves drifted malware detection on publicly available benchmarks and real-world malware databases reported daily by security companies.
  arXiv  Detail & Related papers  (2024-07-18T22:06:20Z)
• Combating Concept Drift with Explanatory Detection and Adaptation for Android Malware Classification [17.399454244765842]
  DREAM is a novel system that improves drift detection and establishes an explanatory adaptation process.<n>Our evaluation shows that DREAM effectively improves the drift detection accuracy and reduces the expert analysis effort in adaptation.
  arXiv  Detail & Related papers  (2024-05-07T07:55:45Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• How Robust are Randomized Smoothing based Defenses to Data Poisoning? [66.80663779176979]
  We present a previously unrecognized threat to robust machine learning models that highlights the importance of training-data quality. We propose a novel bilevel optimization-based data poisoning attack that degrades the robustness guarantees of certifiably robust classifiers. Our attack is effective even when the victim trains the models from scratch using state-of-the-art robust training methods.
  arXiv  Detail & Related papers  (2020-12-02T15:30:21Z)
• Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training [55.824641135682725]
  Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD show that up to 80% of the performance of a system trained on ground-truth data can be recovered.
  arXiv  Detail & Related papers  (2020-11-26T18:51:26Z)
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations [88.94162416324505]
  A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations deviate from the true states, they can mislead the agent into making suboptimal actions. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, is ineffective for many RL tasks.
  arXiv  Detail & Related papers  (2020-03-19T17:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.