mlsanityData to 14 Oct 2026

Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection

arXiv 2605.23623 ↗First posted 22 May 2026cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a longitudinal, drift-aware evaluation of adversarial robustness across more than a decade of Android applications using static and dynamic feature representations extracted from emulator and real-device executions. The dataset is organized into yearly slices and evaluated under three deployment protocols that emulate realistic learning scenarios: (1) same-year training and testing, (2) cross-year deployment without model updates, and (3) expanding-window retraining with cumulative historical data. Across multiple classifier families, adversarial examples are generated using FGSM and SPSA under feasibility constraints. We measure clean performance, Adversarial Accuracy (AA), Attack Success Rate (ASR), and introduce temporal linkage metrics -- RobustDrop, DeltaASR, and Adversarial Amplification Factor (AAF) -- to quantify the relationship between distribution shift and robustness degradation.nResults show that temporal separation is associated with reduced adversarial robustness under the evaluated transfer-based feature-space setting. As the train-test gap increases, clean accuracy and adversarial accuracy decline, while attack success exhibits configuration-dependent increases, particularly under FGSM perturbations and static features. Expanding-window retraining mitigates, but does not eliminate, robustness loss under continued distributional evolution. These findings indicate that temporal drift should be considered when assessing the long-term robustness of intelligent detection systems under evolving data distributions and highlight the need for drift-aware robustness assessment frameworks in long-lived adversarial environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 51 references that are in the map. First posted on arXiv 22 May 2026.

Builds on

19 of 51 references.

References · 19

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  5. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  6. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  7. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  8. 2018TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Timecited by 108
  9. 2017Generating Adversarial Malware Examples for Black-Box Attacks Based on GANcited by 75
  10. 2018Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learningcited by 61
  11. 2020Transcending Transcend: Revisiting Malware Classification in the Presence of Concept Driftcited by 53
  12. 2021EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detectioncited by 13
7 more
  1. 2020Adversarial Concept Drift Detection under Poisoning Attacks for Robust Data Stream Miningcited by 12
  2. 2022Fast & Furious: Modelling Malware Detection as Evolving Data Streamscited by 6
  3. 2018Handling Adversarial Concept Drift in Streaming Datacited by 5
  4. 2023Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutationscited by 3
  5. 2024Adversarial Attacks for Drift Detectioncited by 2
  6. 2025Understanding Concept Drift with Deprecated Permissions in Android Malware Detectioncited by 2
  7. 2025Empirical Evaluation of Concept Drift in ML-Based Android Malware Detectioncited by 2

Built on by

Not cited yet.