Adversarial Example

Adversarial examples are subtly altered inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on improving model robustness against these attacks, exploring techniques like ensemble methods, multi-objective representation learning, and adversarial training, often applied to architectures such as ResNets and Vision Transformers. Understanding and mitigating the threat of adversarial examples is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and natural language processing to malware detection and autonomous driving. The development of robust defenses and effective attack detection methods remains a significant area of ongoing investigation.

Papers

April 14, 2024

Counteracting Concept Drift by Learning with Future Malware Predictions
Branislav Bosansky, Lada Hospodkova, Michal Najman, Maria Rigaki, Elnaz Babayeva, Viliam Lisy
LeArning Abstract Generative Adversarial Network Adversarial Example Adversarial Training Concept Drift Based Malware

April 11, 2024

April 10, 2024

Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data
Yu Qiao, Chaoning Zhang, Apurba Adhikary, Choong Seon Hong
Adversarial Attack Adversarial Example Adversarial Training Raw Data Adversarial Robustness Logit Calibration

April 9, 2024

On adversarial training and the 1 Nearest Neighbor classifier
Amir Hagai, Yair Weiss
Adversarial Example Adversarial Training Adversarial Robustness Nearest Neighbor Classifier

April 8, 2024

April 5, 2024

Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection
João Vitorino, Miguel Silva, Eva Maia, Isabel Praça
Adversarial Example Network Traffic Cyber Attack Detection Network Datasets Adversarial Robustness Benchmark

April 3, 2024

Adversarial Attacks and Dimensionality in Text Classifiers
Nandish Chattopadhyay, Atreya Goswami, Anupam Chattopadhyay
Adversarial Attack Adversarial Example Data Dimensionality Adversarial DEfense Adversarial Vulnerability Text Classifier

April 1, 2024

Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation
Bohao Yang, Kun Zhao, Chen Tang, Dong Liu, Liang Zhan, Chenghua Lin
Large Language Model Adversarial Example Open Domain Dialogue Abstract Meaning Representation Structured Information Adversarial Response

March 30, 2024

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
Renyang Liu, Kwok-Yan Lam, Wei Zhou, Sixing Wu, Jun Zhao, Dongting Hu, Mingming Gong
Native Robustness Adversarial Example Adversarial Training DNN Framework Black Box Attack

March 28, 2024

Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset
Janis Goldzycher, Paul Röttger, Gerold Schneider
Adversarial Example Hate Speech Critical Lesson Individual Annotator Adversarial Data Collection Adversarial Datasets

March 26, 2024

DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection
Sihan Shang, Jiancheng Yang, Zhenglong Sun, Pascal Fua
Adversarial Example Healthcare Data Dataset Watermarking

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

March 22, 2024

Robust optimization for adversarial learning with finite sample complexity guarantees
André Bertolace, Konstatinos Gatsis, Kostas Margellos
Adversarial Attack Native Robustness Adversarial Example Adversarial Learning Sample Complexity Robust Optimization Robust Classifier Classifier Robustness

March 21, 2024

March 19, 2024

As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?
Anjun Hu, Jindong Gu, Francesco Pinto, Konstantinos Kamnitsas, Philip Torr
Adversarial Example Foundation Model Downstream Task Flawed Foundation Adversarial Vulnerability Adversarial Defense

Adversarial Example

Papers

Counteracting Concept Drift by Learning with Future Malware Predictions

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

Persistent Classification: A New Approach to Stability of Data and Adversarial Examples

Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data

On adversarial training and the 1 Nearest Neighbor classifier

David and Goliath: An Empirical Evaluation of Attacks and Defenses for QNNs at the Deep Edge

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack

Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey

Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods

Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection

Adversarial Attacks and Dimensionality in Text Classifiers

Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario

Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset

DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection

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

Robust optimization for adversarial learning with finite sample complexity guarantees

Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking

Reversible Jump Attack to Textual Classifiers with Modification Reduction

As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?