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 3

January 31, 2025

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
Kejia Zhang, Keda Tao, Jiasheng Tang, Huan Wang
LLM Hallucination Mitigating Hallucination Perceptual Adjustment Query Image Noise Poisoning Attack Large Vision Language Model Adversarial Perturbation

January 26, 2025

Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
Hossein Mirzaei, Mojtaba Nafez, Jafar Habibi, Mohammad Sabokrou, Mohammad Hossein Rohban
Data Detection Negative Pair Industrial Anomaly Detection Adversarial Scenario Adversarial Attack Adversarial Training Adversarial Sample Adversarial Perturbation

January 24, 2025

January 19, 2025

Explainable Adversarial Attacks on Coarse-to-Fine Classifiers
Akram Heidarizadeh, Connor Hatfield, Lorenzo Lazzarotto, HanQin Cai, George Atia
Learning Problem Adversarial Instance Adversarial Perturbation Adversarial Attack Traditional Adversarial Layer Wise Relevance Propagation

January 16, 2025

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
Zeyu Wang, Cihang Xie, Brian Bartoldson, Bhavya Kailkhura
Adversarial Perturbation Adversarial Robustness Instruction Tuning Adversarial Fine Tuning Adversarial DEfense

January 8, 2025

LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning
Hafiz Mughees Ahmad, Dario Morle, Afshin Rahimi
Deep Learning Model Adversarial Perturbation Adversarial Attack Data Augmentation Robust Deep

January 3, 2025

January 2, 2025

SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers
Bhavna Gopal, Huanrui Yang, Mark Horton, Yiran Chen
Adversarial Evaluation Adversarial Learning SAfER Instruct Native Robustness Vision Transformer Adversarial Perturbation Layer Selection

December 26, 2024

Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field
Keke Tang, Weiyao Ke, Weilong Peng, Xiaofei Wang, Ziyong Du, Zhize Wu, Peican Zhu, Zhihong Tian
Point Cloud Object Surface 3D Point Cloud Explicit Surface Adversarial Robustness Adversarial Attack Imperceptible Adversarial Adversarial Perturbation

December 25, 2024

Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimization
Ganlin Liu, Ziling Liang, Xiaowei Huang, Xinping Yi, Shi Jin
Neighbor Enhanced Graph Convolutional Network Graph Neural Network DNN Robustness Adversarial Training Adversarial Perturbation Optimization Purpose

December 24, 2024

December 23, 2024

Stability Bounds for the Unfolded Forward-Backward Algorithm
Emilie Chouzenoux, Cecile Della Valle, Jean-Christophe Pesquet
Forward Forward Algorithm Inverse Problem Native Robustness Tikhonov Regularization Adversarial Perturbation

December 17, 2024

Targeted View-Invariant Adversarial Perturbations for 3D Object Recognition
Christian Green, Mehmet Ergezer, Abdurrahman Zeybey
Adversarial Perturbation Recognition Rate Multi View Adversarial Adversarial Attack Adversarial Example Adversarial Noise 3D Object

December 15, 2024

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks
Jin Li, Zitong Yu, Ziqiang He, Z. Jane Wang, Xiangui Kang
Dual System Imperceptible Attack Imperceptible Pattern Unlocking Potential Adversarial Perturbation Optimal Attack Imperceptible Adversarial

December 13, 2024

Adversarial Perturbation

Papers - Page 3

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection

A Note on Implementation Errors in Recent Adaptive Attacks Against Multi-Resolution Self-Ensembles

GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm

Explainable Adversarial Attacks on Coarse-to-Fine Classifiers

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness

LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning

Training-Free Mitigation of Adversarial Attacks on Deep Learning-Based MRI Reconstruction

Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification

SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers

Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field

Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimization

SurvAttack: Black-Box Attack On Survival Models through Ontology-Informed EHR Perturbation

Robustness-aware Automatic Prompt Optimization

Stability Bounds for the Unfolded Forward-Backward Algorithm

Targeted View-Invariant Adversarial Perturbations for 3D Object Recognition

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks

On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models

\textrm{A}^\textrm{2}RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion

Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images

Adversarial Perturbation

Papers - Page 3

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection

A Note on Implementation Errors in Recent Adaptive Attacks Against Multi-Resolution Self-Ensembles

GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm

Explainable Adversarial Attacks on Coarse-to-Fine Classifiers

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness

LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning

Training-Free Mitigation of Adversarial Attacks on Deep Learning-Based MRI Reconstruction

Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification

SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers

Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field

Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimization

SurvAttack: Black-Box Attack On Survival Models through Ontology-Informed EHR Perturbation

Robustness-aware Automatic Prompt Optimization

Stability Bounds for the Unfolded Forward-Backward Algorithm

Targeted View-Invariant Adversarial Perturbations for 3D Object Recognition

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks

On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models

\textrm{A}\textrm{2}RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion

Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images

\textrm{A}^\textrm{2}RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion