Adversarial Data

Adversarial data, encompassing maliciously perturbed inputs designed to mislead machine learning models, poses a significant threat to the reliability of AI systems. Current research focuses on developing robust models through techniques like adversarial training (incorporating adversarial examples during training), and novel detection methods that identify adversarial instances based on distributional discrepancies or feature analysis, often employing diffusion models or ensemble approaches. This field is crucial for ensuring the trustworthiness and security of AI applications across diverse domains, from medical diagnosis and autonomous driving to natural language processing, where adversarial attacks can have serious consequences.

Papers

September 18, 2024

A constrained optimization approach to improve robustness of neural networks
Shudian Zhao, Jan Kronqvist
Neural Network Adversarial Attack Native Robustness Fine Tuning Constrained Optimization Nonconvex Optimization Adversarial Data

August 23, 2024

Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting
Zhenyu Wang, Li Wan, Biqiao Zhang, Yiteng Huang, Shang-Wen Li, Ming Sun, Xin Lei, Zhaojun Yang
Training Data Adversarial Example Keyword Spotting Adversarial Data Disentanglement Framework

August 2, 2024

Trustworthy Machine Learning under Social and Adversarial Data Sources
Han Shao
Machine Learning Adversarial Example Adversarial Behavior Adversarial Data Trustworthy Machine Learning

August 1, 2024

ADBM: Adversarial diffusion bridge model for reliable adversarial purification
Xiao Li, Wenxuan Sun, Huanran Chen, Qiongxiu Li, Yining Liu, Yingzhe He, Jie Shi, Xiaolin Hu
Adversarial Example Adversarial Data Adversarial Purification Adversarial Diffusion

June 18, 2024

Adversarial Attacks on Large Language Models in Medicine
Yifan Yang, Qiao Jin, Furong Huang, Zhiyong Lu
Adversarial Attack Adversarial Data Model Attack Domain Task

May 25, 2024

Detecting Adversarial Data via Perturbation Forgery
Qian Wang, Chen Li, Yuchen Luo, Hefei Ling, Ping Li, Jiazhong Chen, Shijuan Huang, Ning Yu
Adversarial Attack Adversarial Noise Adversarial Detection Adversarial Data Gradient Based Adversarial Specific Forgery

May 23, 2024

Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models
Yiming Chen, Chen Zhang, Danqing Luo, Luis Fernando D'Haro, Robby T. Tan, Haizhou Li
Language Generation Natural Language Generation Adversarial Data Natural Language Generation Datasets

April 9, 2024

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Jianlang Chen, Xuhong Ren, Qing Guo, Felix Juefei-Xu, Di Lin, Wei Feng, Lei Ma, Jianjun Zhao
Adversarial Perturbation Visual Object Tracking Adversarial Data Spatio Temporal Representation

March 5, 2024

BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection
Yu Chen, Liyan Ma, Liping Jing, Jian Yu
Deep Learning Model Adversarial Data Open World Object Detection

February 28, 2024

Catastrophic Overfitting: A Potential Blessing in Disguise
Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
Adversarial Example Adversarial Robustness Adversarial Data Digital STEALTH Metric Fast Adversarial Training Blessing Generation Catastrophic Overfitting

February 13, 2024

Adversarially Robust Feature Learning for Breast Cancer Diagnosis
Degan Hao, Dooman Arefan, Margarita Zuley, Wendie Berg, Shandong Wu
Adversarial Data Breast Cancer Diagnosis Robust Feature

February 3, 2024

MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers
Yatong Bai, Mo Zhou, Vishal M. Patel, Somayeh Sojoudi
Native Robustness Adversarial Robustness Robust Classifier Adversarial Data Mixed Supervised Learning

August 1, 2023

Doubly Robust Instance-Reweighted Adversarial Training
Daouda Sow, Sen Lin, Zhangyang Wang, Yingbin Liang
Adversarial Attack Adversarial Training Robust Version Adversarial Data Importance Weight Adversarial Reweighting

June 22, 2023

Adversarial Resilience in Sequential Prediction via Abstention
Surbhi Goel, Steve Hanneke, Shay Moran, Abhishek Shetty
Adversarial Example Adversarial Robustness Adversarial Scenario Adversarial Data Adversarial Setting Abstention Ability Sequential Prediction

June 2, 2023

VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations
Hoang-Quoc Nguyen-Son, Seira Hidano, Kazuhide Fukushima, Shinsaku Kiyomoto, Isao Echizen
Adversarial Attack Deep Learning Model Training Data Adversarial Text Voter Participation Left Corner Transformation Adversarial Data Hard Label

May 26, 2023

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution
Matías P. Pizarro B., Dorothea Kolossa, Asja Fischer
Adversarial Attack Automatic Speech Recognition Adversarial Example Automatic Speech Recognition System Distinct AInality Trait Adversarial Data Adversarial Audio Output Distribution

May 25, 2023

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
Shuhai Zhang, Feng Liu, Jiahao Yang, Yifan Yang, Changsheng Li, Bo Han, Mingkui Tan
Adversarial Sample Additive Perturbation Adversarial Detection Adversarial Data

April 30, 2023

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama, Mohan Kankanhalli
Adversarial Attack Adversarial Data Adversarial Contrastive Learning Adversarial Regularization

April 21, 2023

RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models
Seulki Park, Daeho Um, Hajung Yoon, Sanghyuk Chun, Sangdoo Yun
Adversarial Text Image Text Matching Adversarial Data Robustness Benchmark V Coco Sg

March 1, 2023

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
Jianing Zhu, Jiangchao Yao, Tongliang Liu, Quanming Yao, Jianliang Xu, Bo Han
Adversarial Training Robust Model Adversarial Data Robustness Problem Federated Adversarial

Adversarial Data

Papers

A constrained optimization approach to improve robustness of neural networks

Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting

Trustworthy Machine Learning under Social and Adversarial Data Sources

ADBM: Adversarial diffusion bridge model for reliable adversarial purification

Adversarial Attacks on Large Language Models in Medicine

Detecting Adversarial Data via Perturbation Forgery

Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection

Catastrophic Overfitting: A Potential Blessing in Disguise

Adversarially Robust Feature Learning for Breast Cancer Diagnosis

MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers

Doubly Robust Instance-Reweighted Adversarial Training

Adversarial Resilience in Sequential Prediction via Abstention

VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning