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.

Papers

July 30, 2024

July 26, 2024

Robust VAEs via Generating Process of Noise Augmented Data
Hiroo Irobe, Wataru Aoki, Kimihiro Yamazaki, Yuhui Zhang, Takumi Nakagawa, Hiroki Waida, Yuichiro Wada, Takafumi Kanamori
Adversarial Attack Adversarial Perturbation Variational Auto

July 23, 2024

S-E Pipeline: A Vision Transformer (ViT) based Resilient Classification Pipeline for Medical Imaging Against Adversarial Attacks
Neha A S, Vivek Chaturvedi, Muhammad Shafique
Adversarial Attack Vision Transformer Adversarial Perturbation Medical Imaging Pipeline System Classification Pipeline

July 18, 2024

Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift
Qingyuan Zeng, Yunpeng Gong, Min Jiang
Adversarial Attack Adversarial Perturbation Task Attack

July 16, 2024

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness
Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu, Kieran Parsons
Adversarial Attack Adversarial Robustness Adversarial Perturbation Randomized Smoothing Enhanced Robustness

July 15, 2024

Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
Rishika Bhagwatkar, Shravan Nayak, Reza Bayat, Alexis Roger, Daniel Z Kaplan, Pouya Bashivan, Irina Rish
Adversarial Attack Vision Language Model Adversarial Robustness Adversarial Perturbation DCU Insight AQ Design Choice Image Attack

July 12, 2024

Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off
Levente Halmosi, Bálint Mohos, Márk Jelasity
Semantic Segmentation Adversarial Robustness Adversarial Perturbation Image Classification Model Robust Segmentation

July 11, 2024

HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks
Raffaele Mura, Giuseppe Floris, Luca Scionis, Giorgio Piras, Maura Pintor, Ambra Demontis, Giorgio Giacinto, Battista Biggio, Fabio Roli
Native Robustness Adversarial Robustness Adversarial Perturbation Hyperparameter Optimization Fast Minimum Norm Attack

July 3, 2024

June 29, 2024

Query-Efficient Hard-Label Black-Box Attack against Vision Transformers
Chao Zhou, Xiaowen Shi, Yuan-Gen Wang
Adversarial Attack Vision Transformer Deep Convolutional Neural Network Adversarial Perturbation Black Box Attack

June 27, 2024

Rethinking and Defending Protective Perturbation in Personalized Diffusion Models
Yixin Liu, Ruoxi Chen, Xun Chen, Lichao Sun
Diffusion Model Adversarial Perturbation Shortcut Learning Pre Trained Text to Image Diffusion Purification Latent Image

June 22, 2024

The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI
Christopher Burger, Charles Walter, Thai Le
Adversarial Attack Explainable AI Adversarial Perturbation XAI Method Text Based Similarity Measure Local Surrogate

June 20, 2024

June 19, 2024

DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection
Zhuoxiao Chen, Zixin Wang, Yadan Luo, Sen Wang, Zi Huang
Pre Trained Model 3D Object Detection Adversarial Perturbation Test Time Adaptation 3D Detector

June 17, 2024

Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness
Kejia Zhang, Juanjuan Weng, Junwei Wu, Guoqing Yang, Shaozi Li, Zhiming Luo
Adversarial Attack Adversarial Training Adversarial Robustness Adversarial Perturbation Graph Convolution

June 13, 2024

Adversarial Perturbation

Papers

Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks

FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks

Robust VAEs via Generating Process of Noise Augmented Data

S-E Pipeline: A Vision Transformer (ViT) based Resilient Classification Pipeline for Medical Imaging Against Adversarial Attacks

Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques

Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off

HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks

$L_p$-norm Distortion-Efficient Adversarial Attack

A Geometric Framework for Adversarial Vulnerability in Machine Learning

Query-Efficient Hard-Label Black-Box Attack against Vision Transformers

Rethinking and Defending Protective Perturbation in Personalized Diffusion Models

The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI

Uniform Convergence of Adversarially Robust Classifiers

Can you trust your explanations? A robustness test for feature attribution methods

DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection

Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness

Towards Evaluating the Robustness of Visual State Space Models

Improving Adversarial Robustness via Feature Pattern Consistency Constraint