Effective Adversarial

Effective adversarial attacks and defenses against machine learning models are a central focus of current research, aiming to improve model robustness and security. Studies explore various attack strategies, including gradient-based methods and those leveraging structural information, across diverse data types like tabular data, images, speech, and text, often employing generative adversarial networks or subspace analysis. These efforts are crucial for evaluating and enhancing the reliability of machine learning systems in critical applications, particularly where security and trustworthiness are paramount, driving the development of provably safe certification methods. The ultimate goal is to create more resilient models capable of withstanding sophisticated adversarial manipulations.

Papers

July 13, 2024

Transferring Structure Knowledge: A New Task to Fake news Detection Towards Cold-Start Propagation
Lingwei Wei, Dou Hu, Wei Zhou, Songlin Hu
Fake News Detection New Task Propagation Environment Cold Start Adaptive Propagation Effective Adversarial

June 2, 2024

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
Thibault Simonetto, Salah Ghamizi, Maxime Cordy
Deep Neural Network Adversarial Robustness Tabular Data Adaptive Attack Tabular Deep Learning Gradient Attack Effective Adversarial

March 24, 2024

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
Rui Zheng, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
Adversarial Attack Adversarial Example Adversarial Perturbation Subspace Learning Clean Speech Subspace Prototype Effective Adversarial

February 4, 2024

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, Miguel Rodrigues
Adversarial Attack Machine Learning Model Adversarial Risk Effective Adversarial

February 2, 2024

STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition
Yi Chang, Zhao Ren, Zixing Zhang, Xin Jing, Kun Qian, Xi Shao, Bin Hu, Tanja Schultz, Björn W. Schuller
Adversarial Attack Adversarial Example Many Sparse Speech Emotion Recognition Transferable Adversarial Attack Effective Adversarial

September 26, 2023

Structure Invariant Transformation for better Adversarial Transferability
Xiaosen Wang, Zeliang Zhang, Jianping Zhang
Adversarial Attack Adversarial Transferability Structural Attack Input Transformation Transfer Based Attack Effective Adversarial

June 2, 2023

A Closer Look at the Adversarial Robustness of Deep Equilibrium Models
Zonghan Yang, Tianyu Pang, Yang Liu
Native Robustness Adversarial Robustness Glance Annotation Adversarial Vulnerability Deep Equilibrium Model Effective Adversarial

September 5, 2022

Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples
Hezekiah J. Branch, Jonathan Rodriguez Cefalu, Jeremy McHugh, Leyla Hujer, Aditya Bahl, Daniel del Castillo Iglesias, Ron Heichman, Ramesh Darwishi
Large Language Model Adversarial Attack Adversarial Example Pre Trained Language Model Effective Adversarial

April 8, 2022

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
Lin Chen, Huaian Chen, Zhixiang Wei, Xin Jin, Xiao Tan, Yi Jin, Enhong Chen
Unsupervised Domain Adaptation Adversarial Learning Task Specific Fast Adversarial Training Bi Discriminator Effective Adversarial

Effective Adversarial

Papers

Transferring Structure Knowledge: A New Task to Fake news Detection Towards Cold-Start Propagation

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition

Structure Invariant Transformation for better Adversarial Transferability

A Closer Look at the Adversarial Robustness of Deep Equilibrium Models

Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation