mlsanityData to 14 Oct 2026

Probabilistic Robustness-driven Universal Adversarial Perturbations with Explainability against Deep Reinforcement Learning-based Intrusion Detection System

arXiv 2609.30605 ↗First posted 24 Sep 2026cs.LGcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

Deep reinforcement learning (DRL) enables adaptive intrusion detection in dynamic network environments but also exposes intrusion detection systems (IDS) to adversarial threats such as universal adversarial perturbations (UAPs), which apply a single input-agnostic perturbation to degrade detection performance across traffic. Probabilistic Robustness (PR), as a post-hoc evaluation metric, provides a principled, population-level measure of adversarial impact that conceptually aligns with the universality objective of UAPs, i.e., PR quantifies the prevalence of misclassification in the input space, making it a natural signal for guiding UAP generation. Hence, we propose PR-based UAP, which represents the first integration of an explicit PR-driven objective into generating UAPs against DRL-based IDS. Building on this formulation, we introduce PX-UAP, which leverages explainable artificial intelligence (XAI) to guide perturbation shaping under realistic domain constraints, and provides a rigorous theoretical analysis of its design. Extensive experiments demonstrate that PX-UAP consistently outperforms state-of-the-art UAP methods in attack effectiveness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 22 of its 42 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

22 of 42 references.

References · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  7. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  9. 2016Universal adversarial perturbationscited by 784
  10. 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
  11. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 66
  12. 2018A Statistical Approach to Assessing Neural Network Robustnesscited by 54
10 more
  1. 2018An Adversarial Approach for Explainable AI in Intrusion Detection Systemscited by 22
  2. 2022PRoA: A Probabilistic Robustness Assessment against Functional Perturbationscited by 19
  3. 2023Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systemscited by 14
  4. 2024ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbationcited by 10
  5. 2024Explainable and Transferable Adversarial Attack for ML-Based Network Intrusion Detectorscited by 7
  6. 2025Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guidecited by 6
  7. 2022FG-UAP: Feature-Gathering Universal Adversarial Perturbationcited by 4
  8. 2025Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devicescited by 2
  9. 2025Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classificationscited by 2
  10. 2025A Novel and Practical Universal Adversarial Perturbations against Deep Reinforcement Learning based Intrusion Detection Systemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
  2. 2025Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
  3. 2024A Survey for Deep Reinforcement Learning Based Network Intrusion Detection
  4. 2023Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks
  5. 2025Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error
  6. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning
  7. 2024VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness
  8. 2024Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey