Adversarial Attack

Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.

Papers

November 16, 2022

Improving Interpretability via Regularization of Neural Activation Sensitivity
Ofir Moshe, Gil Fidel, Ron Bitton, Asaf Shabtai
Deep Neural Network Adversarial Attack Adversarial Robustness Inherent Interpretability Sensitivity Aware

November 9, 2022

November 8, 2022

Preserving Semantics in Textual Adversarial Attacks
David Herel, Hugo Cisneros, Tomas Mikolov
Adversarial Attack Adversarial Example Textual Adversarial Attack Better Adversarial Robustness Semantic Preservation

November 7, 2022

November 5, 2022

Textual Manifold-based Defense Against Natural Language Adversarial Examples
Dang Minh Nguyen, Luu Anh Tuan
Adversarial Attack Adversarial Example Adversarial Text Adversarial Image Textual Adversarial Example Manifold Attack

November 4, 2022

Fairness-aware Regression Robust to Adversarial Attacks
Yulu Jin, Lifeng Lai
Adversarial Attack Fair Machine Learning Fair Regression

November 3, 2022

Adversarial Attack

Papers

Improving Interpretability via Regularization of Neural Activation Sensitivity

Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning

Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation

MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack

Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses

Impact of Adversarial Training on Robustness and Generalizability of Language Models

Robust Smart Home Face Recognition under Starving Federated Data

Are All Edges Necessary? A Unified Framework for Graph Purification

Accountable and Explainable Methods for Complex Reasoning over Text

Preserving Semantics in Textual Adversarial Attacks

Deviations in Representations Induced by Adversarial Attacks

Black-Box Attack against GAN-Generated Image Detector with Contrastive Perturbation

Textual Manifold-based Defense Against Natural Language Adversarial Examples

Fairness-aware Regression Robust to Adversarial Attacks

Visually Adversarial Attacks and Defenses in the Physical World: A Survey

Leveraging Domain Features for Detecting Adversarial Attacks Against Deep Speech Recognition in Noise

Data-free Defense of Black Box Models Against Adversarial Attacks

Isometric Representations in Neural Networks Improve Robustness

Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise

LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification