Adversarial Prediction

Adversarial prediction research explores how to create and defend against inputs designed to mislead machine learning models, focusing on improving model robustness and understanding the underlying vulnerabilities. Current research investigates diverse approaches, including generative models (like GANs and those employing vector quantization), novel activation functions and network architectures, and methods leveraging causal inference to analyze adversarial examples. This field is crucial for enhancing the reliability and security of AI systems across various applications, from medical image analysis and cybersecurity to face recognition and other critical domains where model trustworthiness is paramount.

Papers

July 3, 2024

Non-Adversarial Learning: Vector-Quantized Common Latent Space for Multi-Sequence MRI
Luyi Han, Tao Tan, Tianyu Zhang, Xin Wang, Yuan Gao, Chunyao Lu, Xinglong Liang, Haoran Dou, Yunzhi Huang, Ritse Mann
Latent Space MRI Synthesis Adversarial Prediction Multi Sequence MRI

June 5, 2024

VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise
Zhixun He, Mukesh Singhal
Adversarial Attack Industrial Disturbing Noise U Net Adversarial Noise Adversarial Prediction

May 4, 2024

Your Network May Need to Be Rewritten: Network Adversarial Based on High-Dimensional Function Graph Decomposition
Xiaoyan Su, Yinghao Zhu, Run Li
High Dimensional Network Programming Activation Function Adversarial Prediction

January 30, 2024

Large Language Models in Cybersecurity: State-of-the-Art
Farzad Nourmohammadzadeh Motlagh, Mehrdad Hajizadeh, Mehryar Majd, Pejman Najafi, Feng Cheng, Christoph Meinel
Cybersecurity Perspective LLM Safety Adversarial Prediction

August 28, 2023

Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devices
Samir Rajani, Dario Dematties, Nathaniel Hudson, Kyle Chard, Nicola Ferrier, Rajesh Sankaran, Peter Beckman
Back Propagation Data Distribution Data Leakage Model Weight Training Machine Learning Model Adversarial Prediction

May 25, 2023

PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation
Xianghao Jiao, Yaohua Liu, Jiaxin Gao, Xinyuan Chu, Risheng Liu, Xin Fan
Adversarial Attack Semantic Segmentation Adversarial Perturbation Image Deraining Adversarial Prediction Robust Adversarial Learning

March 16, 2023

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
Huanran Chen, Yichi Zhang, Yinpeng Dong, Xiao Yang, Hang Su, Jun Zhu
Adversarial Attack Adversarial Example Model Ensemble Adversarial Prediction Transfer Based Adversarial Attack

March 2, 2023

Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
Junho Kim, Byung-Kwan Lee, Yong Man Ro
Adversarial Example Adversarial Robustness Instrumental Variable Causal Feature Causal Intervention Robust Network Adversarial Prediction

October 20, 2022

Chaos Theory and Adversarial Robustness
Jonathan S. Kent
Adversarial Attack Adversarial Robustness Cyber Attack Chaos Theory Adversarial Prediction Robustness Radius Loss Input Susceptibility Score

September 30, 2022

Physical Adversarial Attack meets Computer Vision: A Decade Survey
Hui Wei, Hao Tang, Xuemei Jia, Zhixiang Wang, Hanxun Yu, Zhubo Li, Shin'ichi Satoh, Luc Van Gool, Zheng Wang
Deep Neural Network Adversarial Attack Computer Vision Adversarial Perturbation Last Decade Adversarial Prediction

April 6, 2022

Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck
Junho Kim, Byung-Kwan Lee, Yong Man Ro
Adversarial Example Information Bottleneck Model Robustness Adversarial Prediction Non Robust Feature

January 11, 2022

Similarity-based Gray-box Adversarial Attack Against Deep Face Recognition
Hanrui Wang, Shuo Wang, Zhe Jin, Yandan Wang, Cunjian Chen, Massimo Tistarell
Adversarial Example Gray Box Deep Face Recognition Adversarial Prediction

Adversarial Prediction

Papers

Non-Adversarial Learning: Vector-Quantized Common Latent Space for Multi-Sequence MRI

VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise

Your Network May Need to Be Rewritten: Network Adversarial Based on High-Dimensional Function Graph Decomposition

Large Language Models in Cybersecurity: State-of-the-Art

Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devices

PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression

Chaos Theory and Adversarial Robustness

Physical Adversarial Attack meets Computer Vision: A Decade Survey

Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck

Similarity-based Gray-box Adversarial Attack Against Deep Face Recognition