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

arXiv: https://arxiv.org/abs/2609.30605 · HTML: https://mlsanity.com/paper/2609.30605/

## 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.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations](https://mlsanity.com/paper/1801.08092/) (2018)
- [Fast Feature Fool: A data independent approach to universal adversarial perturbations](https://mlsanity.com/paper/1707.05572/) (2017)
- [A Statistical Approach to Assessing Neural Network Robustness](https://mlsanity.com/paper/1811.07209/) (2018)
- [An Adversarial Approach for Explainable AI in Intrusion Detection Systems](https://mlsanity.com/paper/1811.11705/) (2018)
- [PRoA: A Probabilistic Robustness Assessment against Functional Perturbations](https://mlsanity.com/paper/2207.02036/) (2022)
- [Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systems](https://mlsanity.com/paper/2303.06664/) (2023)
- [ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation](https://mlsanity.com/paper/2402.15429/) (2024)
- [Explainable and Transferable Adversarial Attack for ML-Based Network Intrusion Detectors](https://mlsanity.com/paper/2401.10691/) (2024)
- [Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guide](https://mlsanity.com/paper/2502.14833/) (2025)
- [FG-UAP: Feature-Gathering Universal Adversarial Perturbation](https://mlsanity.com/paper/2209.13113/) (2022)
- [Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices](https://mlsanity.com/paper/2506.11892/) (2025)
- [Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications](https://mlsanity.com/paper/2507.00015/) (2025)
- [A Novel and Practical Universal Adversarial Perturbations against Deep Reinforcement Learning based Intrusion Detection Systems](https://mlsanity.com/paper/2511.18223/) (2025)

## 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.