Adversarial Perturbation

Adversarial perturbation research focuses on developing and mitigating the vulnerability of machine learning models to maliciously crafted inputs designed to cause misclassification or other errors. Current research emphasizes improving the robustness of various model architectures, including deep convolutional neural networks, vision transformers, and graph neural networks, often employing techniques like adversarial training, vector quantization, and optimal transport methods. This field is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and face recognition to robotics and natural language processing, by identifying and addressing vulnerabilities to attacks.

423papers

Papers - Page 10

February 16, 2024

Theoretical Understanding of Learning from Adversarial Perturbations
Adversarial Perturbation One Hidden Layer Theoretical Understanding Adversarial Example LeArning Abstract

February 14, 2024

Exploring the Adversarial Capabilities of Large Language Models
Adversarial Capability Adversarial Perturbation Adversarial Example Adversarial Behavior

February 13, 2024

Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
Indoor Robot Navigation Adversarial Attack Adversarial Perturbation Hidden Layer Adversarial Image Traditional Adversarial Native Robustness Free Space Segmentation

February 6, 2024

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
Noise Injection High Efficiency Adversarial Perturbation Critical Neuron Industrial Disturbing Noise Adversarial Robustness Deep Neural Network Adversarial Attack

February 5, 2024

January 28, 2024

Intriguing Equivalence Structures of the Embedding Space of Vision Transformers
Representation Space Vision Transformer Deep Space Model Equivalence Meaningful Representation Adversarial Perturbation

January 26, 2024

AFD: Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement
Adversarial Training Adversarial Fine Tuning Adversarial Sample Adversarial Perturbation Bridging Gap Adversarial Robustness Feature Disentanglement

January 24, 2024

Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint
Neural Network Adversarial Perturbation Robust Generalization Deep Neural Network Robust Overfitting

January 23, 2024

Fast Adversarial Training against Textual Adversarial Attacks
Adversarial Perturbation Textual Adversarial Attack Fast Adversarial Training Adversarial Robustness Adversarial Training

January 22, 2024

January 21, 2024

January 17, 2024

January 6, 2024

Transferable Learned Image Compression-Resistant Adversarial Perturbations
Adversarial Perturbation Transferable Visual Adversarial Attack Image Compression

January 4, 2024

Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging
Adversarial Perturbation Multimodal Vision Language Model Adversarial Example Adversarial Manipulation Adversarial Attack Textual Demonstration Pathology Imaging Robust Defense

December 21, 2023

ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks
Neural Network Adversarial Perturbation Supervised ImageNet Adversarial Robustness

December 20, 2023

Doubly Perturbed Task Free Continual Learning
FL Framework Catastrophic Forgetting Adversarial Perturbation Online Continual Learning Free Continual Learning

Adversarial Perturbation

Papers - Page 10

Theoretical Understanding of Learning from Adversarial Perturbations

Exploring the Adversarial Capabilities of Large Language Models

Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons

Generalization Properties of Adversarial Training for \ell_0-Bounded Adversarial Attacks

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics

Intriguing Equivalence Structures of the Embedding Space of Vision Transformers

AFD: Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement

Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint

Fast Adversarial Training against Textual Adversarial Attacks

Robustness to distribution shifts of compressed networks for edge devices

Adversarial speech for voice privacy protection from Personalized Speech generation

Efficient local linearity regularization to overcome catastrophic overfitting

How Robust Are Energy-Based Models Trained With Equilibrium Propagation?

A GAN-based data poisoning framework against anomaly detection in vertical federated learning

Rethinking Impersonation and Dodging Attacks on Face Recognition Systems

Transferable Learned Image Compression-Resistant Adversarial Perturbations

Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging

ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks

Doubly Perturbed Task Free Continual Learning