Adversarial Generation

Adversarial generation focuses on creating inputs—images, time series, text, or 3D models—designed to fool machine learning models, revealing vulnerabilities and improving model robustness. Current research emphasizes generating these adversarial examples across diverse data types and model architectures, employing techniques like generative adversarial networks (GANs), score-based models, and even large language models to automate the attack design process. This research is crucial for assessing the security and reliability of machine learning systems in various applications, from image recognition and financial modeling to autonomous driving and cybersecurity. The development of more sophisticated adversarial generation methods drives the creation of more robust and resilient AI systems.

Papers

July 17, 2024

Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection
Youheng Sun, Shengming Yuan, Xuanhan Wang, Lianli Gao, Jingkuan Song
Adversarial Attack Adversarial Example Target Amazon Ally Adversarial Generation Common Cause

June 14, 2024

Universal randomised signatures for generative time series modelling
Francesca Biagini, Lukas Gonon, Niklas Walter
Reservoir Computing Universal Image Neural Stochastic Differential Equation Handwritten Signature Adversarial Generation Path Signature Generative Time Series Randomized Signature

June 5, 2024

GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats
Sangeek Hyun, Jae-Pil Heo
Gaussian Process Gaussian Splatting 3D Generative Adversarial Generation 3D Generative Adversarial Network

January 27, 2024

L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
Ping Guo, Fei Liu, Xi Lin, Qingchuan Zhao, Qingfu Zhang
Adversarial Attack Adversarial Generation Decision Based

January 24, 2024

Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size
Junlin Liu, Xinchen Lyu
Adversarial Example Task Transferability Adversarial Image Step Size Adversarial Framework Adversarial Generation Local Mixup

October 21, 2023

Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
Ayberk Aydin, Alptekin Temizel
Adversarial Example Adversarial Perturbation Distance Metric Color Space Adversarial Generation Spatial Transformation Perceptual Distance

October 12, 2023

CleftGAN: Adapting A Style-Based Generative Adversarial Network To Create Images Depicting Cleft Lip Deformity
Abdullah Hayajneh, Erchin Serpedin, Mohammad Shaqfeh, Graeme Glass, Mitchell A. Stotland
Adversarial Generation Style Based Generative Adversarial Network CLEFT Lip

October 6, 2023

Assessing Robustness via Score-Based Adversarial Image Generation
Marcel Kollovieh, Lukas Gosch, Yan Scholten, Marten Lienen, Stephan Günnemann
Adversarial Attack Native Robustness Adversarial Example Score Based Generative Adversarial Generation Unrestricted Adversarial

September 3, 2023

SOAR: Scene-debiasing Open-set Action Recognition
Yuanhao Zhai, Ziyi Liu, Zhenyu Wu, Yi Wu, Chunluan Zhou, David Doermann, Junsong Yuan, Gang Hua
Action Recognition Open Set Adversarial Generation Source Bias

August 8, 2023

PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation
Zhu Liu, Jinyuan Liu, Benzhuang Zhang, Long Ma, Xin Fan, Risheng Liu
Image Fusion Visible Image Fusion Adversarial Generation Robust Semantic Segmentation Infrared Visible Image Fusion

May 18, 2023

Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation
Soumyadeep Hore, Jalal Ghadermazi, Diwas Paudel, Ankit Shah, Tapas K. Das, Nathaniel D. Bastian
Adversarial Attack Network Intrusion Detection Evasion Attack Adversarial Generation Successful Adversarial Attack

April 10, 2023

Generating Adversarial Attacks in the Latent Space
Nitish Shukla, Sudipta Banerjee
Adversarial Attack Generative Adversarial Network Latent Space Adversarial Perturbation Margin Based Adversarial Generation

March 29, 2023

A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion
Haomin Zhuang, Yihua Zhang, Sijia Liu
Adversarial Attack Adversarial Robustness Stable Diffusion Adversarial Prompt Pilot Study Adversarial Generation QuEry Based Attack

September 30, 2022

Understanding Pure CLIP Guidance for Voxel Grid NeRF Models
Han-Hung Lee, Angel X. Chang
Image Augmentation 3D Object Generation Learning Problem Adversarial Generation Grid Based NeRF

September 27, 2022

V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perception
Hao Xiang, Runsheng Xu, Xin Xia, Zhaoliang Zheng, Bolei Zhou, Jiaqi Ma
Autonomous Vehicle Perception Aware Adversarial Generation LiDAR Equipped

August 28, 2022

Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies
Yinghua Zhang, Yangqiu Song, Kun Bai, Qiang Yang
Adversarial Attack Adversarial Example New Attack Fine Tuned Model Adversarial Generation Transfer Evolutionary Optimization

August 20, 2022

Evaluating Out-of-Distribution Detectors Through Adversarial Generation of Outliers
Sangwoong Yoon, Jinwon Choi, Yonghyeon Lee, Yung-Kyun Noh, Frank Chongwoo Park
Robustness Evaluation Distribution Detector Adversarial Generation Structural Outlier

June 17, 2022

Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation
Wen Sun, Jian Jin, Weisi Lin
Adversarial Example Loss Function Image Generation Adversarial Image Adversarial Loss Adversarial Generation Noticeable Difference

May 1, 2022

A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictions
Yong Xie, Dakuo Wang, Pin-Yu Chen, Jinjun Xiong, Sijia Liu, Sanmi Koyejo
Adversarial Attack Real Text Word Adversarial Setting Stock Price Forecasting Adversarial Generation Victim Model

January 30, 2022

Autoencoding Hyperbolic Representation for Adversarial Generation
Eric Qu, Dongmian Zou
Hyperbolic Representation Adversarial Generation

Adversarial Generation

Papers

Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection

Universal randomised signatures for generative time series modelling

GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats

L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks

Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size

Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces

CleftGAN: Adapting A Style-Based Generative Adversarial Network To Create Images Depicting Cleft Lip Deformity

Assessing Robustness via Score-Based Adversarial Image Generation

SOAR: Scene-debiasing Open-set Action Recognition

PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation

Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation

Generating Adversarial Attacks in the Latent Space

A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion

Understanding Pure CLIP Guidance for Voxel Grid NeRF Models

V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perception

Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies

Evaluating Out-of-Distribution Detectors Through Adversarial Generation of Outliers

Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation

A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictions

Autoencoding Hyperbolic Representation for Adversarial Generation