Realistic Adversarial

Realistic adversarial attacks aim to create adversarial examples that are plausible and effective in real-world scenarios, unlike many previous studies focusing on unrealistic perturbations. Current research emphasizes developing methods to generate these realistic attacks across various domains, including image classification, natural language processing, and network security, often employing techniques like generative adversarial networks (GANs), diffusion models, and reinforcement learning to craft subtle yet impactful perturbations. This focus on realism is crucial for improving the robustness of machine learning models in practical applications and for developing more effective defense mechanisms against real-world threats.

Papers

August 11, 2024

PhishLang: A Lightweight, Client-Side Phishing Detection Framework using MobileBERT for Real-Time, Explainable Threat Mitigation
Sayak Saha Roy, Shirin Nilizadeh
Data Detection High Explainability Realistic Adversarial Lightweight Large Language Model Url Detection

June 25, 2024

CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems
Zhen Chen, Yong Liao, Youpeng Zhao, Zipeng Dai, Jian Zhao
Adversarial Attack Constructive Approach Cooperative Multi Agent Reinforcement Learning Malicious Agent Cooperative Multi Agent System Adversarial Markov Decision Process CUDA Implementation Realistic Adversarial Adversarial Capability

December 18, 2023

Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model
Decheng Liu, Xijun Wang, Chunlei Peng, Nannan Wang, Ruiming Hu, Xinbo Gao
Adversarial Attack Image Generation Latent Diffusion Model Imperceptible Adversarial Perturbation Diffusion Based Framework Adversarial Face Realistic Adversarial

August 13, 2023

SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detection
João Vitorino, Isabel Praça, Eva Maia
Adversarial Attack Adversarial Example Network Intrusion Detection Realistic Adversarial Knowledge Organization

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

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 26, 2022

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks
Xingxing Wei, Ying Guo, Jie Yu, Bo Zhang
Adversarial Attack Adversarial Patch Product Specific Position Information Additive Perturbation Adversarial Patch Attack Realistic Adversarial

September 19, 2022

AdvDO: Realistic Adversarial Attacks for Trajectory Prediction
Yulong Cao, Chaowei Xiao, Anima Anandkumar, Danfei Xu, Marco Pavone
Adversarial Attack Autonomous Vehicle Adversarial Robustness Trajectory Prediction Realistic Adversarial Adversarial Trajectory

August 12, 2022

Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator
Xiangbo Gao, Cheng Luo, Qinliang Lin, Weicheng Xie, Minmin Liu, Linlin Shen, Keerthy Kusumam, Siyang Song
Adversarial Attack Adversarial Example Patch Generation Realistic Adversarial Fast Minimum Norm Attack Task Attack

June 3, 2022

The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images
Zhengyu Zhao, Nga Dang, Martha Larson
Real World Importance Aware Generative Adversarial Complex Pattern Adversarial Image Realistic Adversarial

March 19, 2022

Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense
Thai Le, Jooyoung Lee, Kevin Yen, Yifan Hu, Dongwon Lee
Wild Challenge Adversarial Text Additive Perturbation Toxic Text Realistic Adversarial

March 8, 2022

Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection
João Vitorino, Nuno Oliveira, Isabel Praça
Adversarial Attack Adversarial Example Adversarial Training Intrusion Detection Untargeted Attack Realistic Adversarial Perturbation Artifact

February 7, 2022

On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks
Salijona Dyrmishi, Salah Ghamizi, Thibault Simonetto, Yves Le Traon, Maxime Cordy
Adversarial Example Adversarial Robustness Real World Attack Realistic Adversarial

Realistic Adversarial

Papers

PhishLang: A Lightweight, Client-Side Phishing Detection Framework using MobileBERT for Real-Time, Explainable Threat Mitigation

CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems

Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model

SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detection

URET: Universal Robustness Evaluation Toolkit (for Evasion)

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

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks

AdvDO: Realistic Adversarial Attacks for Trajectory Prediction

Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator

The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images

Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense

Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection

On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks