• Home
  • Search
  • A Method To Study The Robustness Of ML Models Against Adversarial Attacks
  • https://doi.org/10.64252/dpk19t90Copy DOI Icon

A Method To Study The Robustness Of ML Models Against Adversarial Attacks

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

This invention presents a novel method for evaluating and enhancing the robustness of machine learning (ML) models against adversarial attacks. Adversarial attacks, which involve small perturbations to input data that mislead models into making incorrect predictions, pose significant risks, particularly in safety-critical applications such as autonomous vehicles, healthcare systems, and security frameworks. Traditional methods for assessing model robustness, such as accuracy and precision, fail to account for adversarial vulnerabilities, leaving ML systems susceptible to exploitation. The proposed method introduces a comprehensive evaluation framework that rigorously tests models under various adversarial attack scenarios, providing a more accurate and realistic assessment of their resilience. This approach ensures that models are subjected to a diverse range of adversarial threats, helping identify weaknesses that may not be apparent under standard conditions. In addition, the invention incorporates refined adversarial training techniques that expose models to a broad spectrum of adversarial examples, enabling them to learn robust patterns while maintaining performance on non-adversarial inputs. Complementing adversarial training, advanced optimization techniques are employed to enhance the model's inherent resistance to adversarial perturbations, thereby improving overall security. A significant contribution of this invention is the real-time adversarial attack detection system, which allows models to identify and mitigate adversarial manipulations during deployment, adding an extra layer of protection. Moreover, the invention supports custom defense mechanisms tailored to specific machine learning architectures, ensuring that defense strategies are optimized for different model types. This method offers a scalable, adaptable, and practical solution for enhancing the security of machine learning models, thereby making them more reliable and resilient against adversarial threats in real-world applications.

Similar Papers
  • Research Article
  • Citations3

A Comparative Analysis of Adversarial Attack Methods on Machine Learning Models

  • Sep 04, 2024
  • INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
  • Abdirashid Abukar Ahmed +1
  • Conference Article
  • Citations26

Detecting Adversarial Examples Using Data Manifolds

  • Oct 01, 2018
  • Susmit Jha +3
  • Research Article

A Hierarchical Deep Learning Architecture for Robust Intrusion Detection in Time-Evolving Security Landscapes

  • Feb 29, 2024
  • International Journal for Research in Applied Science and Engineering Technology
  • Shashank R R +2
  • Research Article
  • Citations59

A simple framework to enhance the adversarial robustness of deep learning-based intrusion detection system

  • Dec 10, 2023
  • Computers & Security
  • Xinwei Yuan +5
  • Conference Article
  • Citations3

Mal-LSGAN: An Effective Adversarial Malware Example Generation Model

  • Dec 01, 2021
  • Jianhua Wang +5
  • Research Article
  • Citations66

Untargeted white-box adversarial attack with heuristic defence methods in real-time deep learning based network intrusion detection system

  • Oct 11, 2023
  • Computer Communications
  • Khushnaseeb Roshan +2
  • PDF
  • Research Article
  • Citations5

Universal Adversarial Training Using Auxiliary Conditional Generative Model-Based Adversarial Attack Generation

  • Jul 31, 2023
  • Applied Sciences
  • Hiskias Dingeto +1
  • Research Article

Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizers

  • Jan 01, 2025
  • IEEE Transactions on Signal Processing
  • Elad Sofer +3
  • Research Article
  • Citations21

Adversarial Machine Learning in Cybersecurity: Vulnerabilities and Defense Strategies

  • Jan 01, 2020
  • Journal of Frontiers in Multidisciplinary Research
  • Lawal Abdulmutalib Babatunde +6
  • Research Article
  • Citations21

Robust Attacks Detection Model for Internet of Flying Things Based on Generative Adversarial Network (GAN) and Adversarial Training

  • Jul 01, 2025
  • IEEE Internet of Things Journal
  • Tarek Gaber +3
  • Research Article

SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL

  • Aug 15, 2024
  • Dalat University Journal of Science
  • Thanh Son Phan +3
  • Research Article
  • Citations27

Defending against adversarial machine learning attacks using hierarchical learning: A case study on network traffic attack classification

  • Dec 17, 2022
  • Journal of Information Security and Applications
  • Andrew Mccarthy +3
  • Research Article
  • Citations1

Adversarial Training and Robustness in Machine Learning Frameworks

  • Mar 22, 2024
  • International Journal of Advanced Research in Science, Communication and Technology
  • Mrs Sangeetha G +3
  • Research Article
  • Citations20

Towards robust autonomous driving systems through adversarial test set generation

  • Nov 17, 2022
  • ISA Transactions
  • Devrim Unal +4
  • Research Article
  • Citations33

Statistical Detection of Adversarial Examples in Blockchain-Based Federated Forest In-Vehicle Network Intrusion Detection Systems

  • Jan 01, 2022
  • IEEE Access
  • Ibrahim Aliyu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.