☆ 4.7 Article

Adversarial machine learning for network intrusion detection: A comparative study

COMPUTER NETWORKS (2022)

Related references

Note: Only part of the references are listed.

Article Computer Science, Theory & Methods

Network Traffic Generation: A Survey and Methodology

Oluwamayowa Ade Adeleke et al.

Summary: This article provides an overview of the widespread utilization of network traffic workloads in applied research. It includes a comprehensive survey of traffic generators referenced by researchers over the last 13 years, categorizing their functional behaviors in-depth. These classifications are then used to develop a methodology for selecting generators based on the workload requirements of future research.

ACM COMPUTING SURVEYS (2023)

Add to Collection

Article Computer Science, Theory & Methods

FGMD: A robust detector against adversarial attacks in the IoT network

Hongling Jiang et al.

Summary: Due to the increasing reliance on machine learning models for network intrusion detectors in the Internet of Things (IoT), attacks against these detectors are also on the rise. Existing solutions for adversarial attacks against IoT networks are rare and have limitations. To address this problem, we propose an algorithm to generate adversarial samples and evaluate the performance of the IoT network intrusion detector. We also present a novel framework, FGMD (Feature Grouping and Multi-model fusion Detector), that can defend against adversarial attacks through feature grouping and multi model fusion. Experimental results demonstrate the effectiveness of FGMD against adversarial attacks.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2022)

Add to Collection

Article Computer Science, Information Systems

Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection

Joao Vitorino et al.

Summary: Adversarial attacks pose a major threat to machine learning and systems that rely on it. This paper proposes an adaptive perturbation pattern method for generating realistic adversarial examples in a gray-box setting. The method is evaluated in a cybersecurity case study, showing its effectiveness in generating realistic adversarial examples, which can be advantageous for both adversarial training and attacks.

FUTURE INTERNET (2022)

Add to Collection

Article Telecommunications

The robust deep learning-based schemes for intrusion detection in Internet of Things environments

Xingbing Fu et al.

Summary: With the rise of IoT, network attacks have become more diversified and intelligent, highlighting the importance of IDS for network security. This study tested the robustness of three IDS models and found that CNN was the most robust to adversarial examples under normal training, while GRU and LSTM significantly improved their robustness after adversarial training.

ANNALS OF TELECOMMUNICATIONS (2021)

Add to Collection

Article Computer Science, Information Systems

Hardening machine learning denial of service (DoS) defences against adversarial attacks in IoT smart home networks

Eirini Anthi et al.

Summary: Machine learning based IDS can efficiently detect cyberattacks in IoT networks, but they are vulnerable to AML attacks. AML can manipulate data and network traffic to confuse machine learning classifiers, leading to misclassification of malicious network packets. The paper proposes a rule-based approach to generate AML attack samples and explores their impact on supervised machine learning classifiers used in IoT networks.

COMPUTERS & SECURITY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Evaluating and Improving Adversarial Robustness of Machine Learning-Based Network Intrusion Detectors

Dongqi Han et al.

Summary: This study systematically examines the use of ML/DL in NIDS, proposing a method for evaluating NIDS robustness through adversarial attacks in gray/black-box traffic space and offering a defense scheme. Experimental results demonstrate the effectiveness of the proposed attack and the ability of the defense method to mitigate such attacks.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Improving Decision-Making-Process for Robot Navigation Under Uncertainty

Mohamed Ibn Khedher et al.

Summary: This paper focuses on robot navigation in uncertain environments, proposing an efficient decision-making model based on Deep Neural Network (DNN) and utilizing adversarial training based on data augmentation to improve robot decisions. The research explores data augmentation with uncertainty noise to enhance the robustness and performance of the decision model, while also considering Efficiency and Pareto Front metrics to select the optimal data augmentation rate.

ICAART: PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 2 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Analyzing Adversarial Attacks against Deep Learning for Robot Navigation

Mohamed Ibn Khedher et al.

Summary: The autonomous system sector is evolving rapidly, with particular focus on the navigation of autonomous robots in complex environments. Decision-making models based on Deep Neural Networks and defensive techniques like adversarial training are being explored to enhance the robustness of robot decisions in uncertain environments.

ICAART: PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 2 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Dynamic and Scalable Deep Neural Network Verification Algorithm

Mohamed Ibn Khedher et al.

Summary: This paper proposes an efficient technique for verifying feed-forward neural networks properties, showcasing robustness through the introduction of different neural network scenarios. The technique is based on linearizing the non-convex ReLU activation function using Big-M optimization and iteratively finding the largest input range to verify neural network properties.

ICAART: PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 2 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Mathematical Programming Approach for Adversarial Attack Modelling

Hatem Ibn-Khedher et al.

Summary: In this paper, a new formulation based on linear programming approach is proposed for modelling adversarial attacks, considering noised inputs while reaching the optimal perturbation. The algorithm's decision behavior is evaluated in different neural network scales, quantifying performance based on factors such as total perturbation cost and percentage of perturbed inputs.

ICAART: PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 2 (2021)

Add to Collection

Article Multidisciplinary Sciences

DReLAB - Deep REinforcement Learning Adversarial Botnet: A benchmark dataset for adversarial attacks against botnet Intrusion Detection Systems

Andrea Venturi et al.

Summary: This research introduces a dataset with adversarial samples generated using Deep Reinforcement Learning techniques to test the resilience of botnet detectors against adversarial attacks. The dataset is able to evade state of the art detectors and serves as an important contribution to the cybersecurity research community.

DATA IN BRIEF (2021)

Add to Collection

Article Computer Science, Information Systems

Adversarial attack-based security vulnerability verification using deep learning library for multimedia video surveillance

JaeHan Jeong et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2020)

Add to Collection

Article Engineering, Multidisciplinary

Adversarial Attacks and Defenses in Deep Learning

Kui Ren et al.

ENGINEERING (2020)

Add to Collection

Article Computer Science, Hardware & Architecture

Deep learning methods in network intrusion detection: A survey and an objective comparison

Sunanda Gamage et al.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2020)

Add to Collection

Article Computer Science, Information Systems

Deep Reinforcement Adversarial Learning Against Botnet Evasion Attacks

Giovanni Apruzzese et al.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm

Ayyaz Ul Haq Qureshi et al.

COMPUTERS (2020)

Add to Collection

Article Computer Science, Information Systems

A Brute-Force Black-Box Method to Attack Machine Learning-Based Systems in Cybersecurity

Sicong Zhang et al.

IEEE ACCESS (2020)

Add to Collection

Review Automation & Control Systems

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Han Xu et al.

INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING (2020)

Add to Collection

Article Computer Science, Information Systems

Survey on SDN based network intrusion detection system using machine learning approaches

Nasrin Sultana et al.

PEER-TO-PEER NETWORKING AND APPLICATIONS (2019)

Add to Collection

Review Computer Science, Hardware & Architecture

A holistic review of Network Anomaly Detection Systems: A comprehensive survey

Nour Moustafa et al.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2019)

Add to Collection

Article Computer Science, Theory & Methods

Towards the development of realistic botnet dataset in the Internet of Things for network forensic analytics: Bot-IoT dataset

Nickolaos Koroniotis et al.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2019)

Add to Collection

Article Computer Science, Theory & Methods

The security of machine learning in an adversarial setting: A survey

Xianmin Wang et al.

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING (2019)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Evaluating Deep Learning Based Network Intrusion Detection System in Adversarial Environment

Ye Peng et al.

PROCEEDINGS OF 2019 IEEE 9TH INTERNATIONAL CONFERENCE ON ELECTRONICS INFORMATION AND EMERGENCY COMMUNICATION (ICEIEC 2019) (2019)

Add to Collection

Article Computer Science, Information Systems

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Naveed Akhtar et al.

IEEE ACCESS (2018)

Add to Collection

Article Computer Science, Information Systems

Deep Learning-Based Intrusion Detection with Adversaries

Zheng Wang

IEEE ACCESS (2018)

Add to Collection

Article Computer Science, Information Systems

EclipseloT: A secure and adaptive hub for the Internet of Things

Eirini Anthi et al.

COMPUTERS & SECURITY (2018)

Add to Collection

Article Computer Science, Information Systems

A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection

Anna L. Buczak et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2016)

Add to Collection

Article Computer Science, Information Systems

An empirical comparison of botnet detection methods

S. Garcia et al.

COMPUTERS & SECURITY (2014)

Add to Collection

© Peeref 2019-2024. All rights reserved.