Adversarial Evasion Attack

Adversarial evasion attacks exploit vulnerabilities in machine learning models by subtly altering inputs to cause misclassification, aiming to understand and mitigate these weaknesses. Current research focuses on analyzing attack effectiveness across various model types, including large language models and those used in autonomous driving and network security, often employing techniques like generative adversarial networks and reinforcement learning to craft these "adversarial examples." This research is crucial for enhancing the robustness and reliability of machine learning systems in safety-critical applications, such as autonomous vehicles and cybersecurity, where model failures can have significant consequences. The development of robust defenses against these attacks is a key area of ongoing investigation.

Papers

October 15, 2024

Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
Kevin Eykholt, Farhan Ahmed, Pratik Vaishnavi, Amir Rahmati
Adversarial Attack Adversarial Learning Camera Lens Critical Review Adversarial Scenario Evasion Attack Adversarial Threat Adversarial Evasion Attack

September 11, 2024

Introducing Perturb-ability Score (PS) to Enhance Robustness Against Evasion Adversarial Attacks on ML-NIDS
Mohamed elShehaby, Ashraf Matrawy
Adversarial Attack Native Robustness Network Intrusion Detection Feature Perturbation Adversarial Evasion Attack Network Intrusion Detection System

June 12, 2024

Adversarial Evasion Attack Efficiency against Large Language Models
João Vitorino, Eva Maia, Isabel Praça
Adversarial Attack Adversarial Example Adversarial Defense Word Level Attack Adversarial Evasion Attack

December 28, 2023

Attack Tree Analysis for Adversarial Evasion Attacks
Yuki Yamaguchi, Toshiaki Aoki
Machine Learning Adversarial Attack Adversarial Evasion Attack Attack Tree

December 3, 2023

OA-ECBVC: A Cooperative Collision-free Encirclement and Capture Approach in Cluttered Environments
Xinyi Wang, Yulong Ding, Yizhou Chen, Ruihua Han, Lele Xi, Ben M. Chen
Collision Avoidance Collision Free Cluttered Environment Voronoi Tessellation Capturing Maneuver Adversarial Evasion Attack Obstacle Scenario Obstacle Cluttered Environment

August 23, 2023

Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack
Ningfei Wang, Yunpeng Luo, Takami Sato, Kaidi Xu, Qi Alfred Chen
Adversarial Attack Autonomous Driving Evasion Attack Driving Policy Physical Adversarial Adversarial Evasion Attack System Level

August 3, 2023

URET: Universal Robustness Evaluation Toolkit (for Evasion)
Kevin Eykholt, Taesung Lee, Douglas Schales, Jiyong Jang, Ian Molloy, Masha Zorin
Adversarial Example Adversarial Input Robustness Evaluation Adversarial Evasion Attack Realistic Adversarial

June 8, 2023

Adversarial Evasion Attacks Practicality in Networks: Testing the Impact of Dynamic Learning
Mohamed el Shehaby, Ashraf Matrawy
Adversarial Attack Global Impact Network Programming Dynamic Learning Adversarial Evasion Attack Network Intrusion Detection System Based NIDS

March 13, 2023

Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systems
Islam Debicha, Benjamin Cochez, Tayeb Kenaza, Thibault Debatty, Jean-Michel Dricot, Wim Mees
Machine Learning Adversarial Attack Machine Learning Model Adversarial Example Narrative Review Machine Learning Algorithm Network Intrusion Detection Task Feasibility Adversarial Evasion Attack

January 30, 2023

Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification
João Vitorino, Isabel Praça, Eva Maia
Adversarial Attack Adversarial Example Classification Code Robust Learning IoT Intrusion Detection Adversarial Evasion Attack Realistic Adversarial

December 5, 2022

Efficient Malware Analysis Using Metric Embeddings
Ethan M. Rudd, David Krisiloff, Scott Coull, Daniel Olszewski, Edward Raff, James Holt
Metric Learning Malware Detection Adversarial Evasion Attack Metric Embeddings

October 6, 2022

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection
Rizwan Hamid Randhawa, Nauman Aslam, Mohammad Alauthman, Muhammad Khalid, Husnain Rafiq
Deep Reinforcement Learning GAN Training Adversarial Evasion Attack BotNet Detection

February 25, 2022

Projective Ranking-based GNN Evasion Attacks
He Zhang, Xingliang Yuan, Chuan Zhou, Shirui Pan
Adversarial Attack Adversarial Sample Attack Strategy Adversarial Evasion Attack Projective Simulation Learning Based Attack

February 15, 2022

Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustness
Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil
Loss Function Adversarial Robustness Adversarial Sample Standard Deep Adversarial Evasion Attack Deep Attack

Adversarial Evasion Attack

Papers

Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks

Introducing Perturb-ability Score (PS) to Enhance Robustness Against Evasion Adversarial Attacks on ML-NIDS

Adversarial Evasion Attack Efficiency against Large Language Models

Attack Tree Analysis for Adversarial Evasion Attacks

OA-ECBVC: A Cooperative Collision-free Encirclement and Capture Approach in Cluttered Environments

Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack

URET: Universal Robustness Evaluation Toolkit (for Evasion)

Adversarial Evasion Attacks Practicality in Networks: Testing the Impact of Dynamic Learning

Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systems

Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification

Efficient Malware Analysis Using Metric Embeddings

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection

Projective Ranking-based GNN Evasion Attacks

Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustness