Skip to content

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

Sep 2026 · arXiv.org · Vol abs/2609.30605 · 0 citations · 42 references
Computer Science

TL;DR

This work proposes PR-based UAP, which represents the first integration of an explicit PR-driven objective into generating UAPs against DRL-based IDS and introduces 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.

Abstract

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.

View source

Similar papers

Open access 2026

A Sensitivity-Driven Gradient Framework for Adversarial Sample Generation in Deep Learning-Based Network Intrusion Detection Systems

A sensitivity-driven adversarial generation framework (AGF) that identifies and perturbs the most influential traffic features that affect the classifier’s decision boundary to generate statistically consistent adversarial samples with constrained perturbation magnitude is proposed.

Omar Abboosh Hussein Gwassi, O. N. Uçan · 0 citations
Open access Sep 2026

Adversarially robust few-shot learning for aI-enabled attack mitigation in the internet of things

The rapid expansion of Internet of Things (IoT) environments has introduced significant security challenges, particularly due to limited labeled data and increasing vulnerability to adversarial attacks. Traditional intrusion detection systems (IDS) struggle to generalize under such constraints, while existing few-shot...

Fatima A. Asiri, Nazik Alturki, Noha Alnazzawi et al. · 0 citations
#explainable ai Open access Sep 2026

Estimating adversarial transferability from feature-importance similarity in explainable intrusion detection systems

This study investigates the transferability of adversarial attacks across XGBoost and LightGBM models in IDS and uses Explainable AI (XAI) techniques to identify features that influence model decisions and shows that feature-importance patterns can be used to examine model vulnerability under adversarial perturbations.

Abdlelah Abdlatef, Marwa D. Abdulkareem, Duygu Çakır · 2 citations
#artificial intelligence Open access Oct 2026

A deep generative adversarial framework with rat-optimized feature selection for efficient intrusion detection in large-scale cloud network traffic environments

Cloud computing is a fundamental paradigm in modern computing; however, its distributed and multi-tenant nature increases exposure to cyber threats, making effective intrusion detection essential. Despite recent advances in artificial intelligence–based intrusion detection systems (IDS), many existing approaches remain...

S. Priya, K. Tamilarasi, V. Sharma et al. · 0 citations
Conference Open access Sep 2026

Adversarial Optimization Scheme for Threat Detection Based on Hierarchical Oracle Supervision

This study introduces an adversarial training optimization framework that incorporates hierarchical label encoding and prompt learning, designed to enhance model robustness and generalization in threat detection.

Yi-Qing Luo, Ming-Shu He, Xiao-Juan Wang · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.