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

August 26, 2024

TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
Zelin Li, Kehai Chen, Lemao Liu, Xuefeng Bai, Mingming Yang, Yang Xiang, Min Zhang
Large Language Model Adversarial Attack Fast Adversarial Training

August 24, 2024

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach
Jiwei Guan, Tianyu Ding, Longbing Cao, Lei Pan, Chen Wang, Xi Zheng
Adversarial Attack Native Robustness Adversarial Robustness Vision Language Adversarial Perturbation Adversarial Vulnerability Multimodal Attack

August 23, 2024

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
Zhenyu Liu, Haoran Duan, Huizhi Liang, Yang Long, Vaclav Snasel, Guiseppe Nicosia, Rajiv Ranjan, Varun Ojha
Adversarial Attack Adversarial Example Adversarial Training Model Robustness Neural Network Robustness Adversarial Distillation Adversarial Discriminator

August 22, 2024

August 21, 2024

August 20, 2024

August 19, 2024

Adversarial Attack

Papers

TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks

BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks

Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing

Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attacks

Query-Efficient Video Adversarial Attack with Stylized Logo

First line of defense: A robust first layer mitigates adversarial attacks

Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection

Correlation Analysis of Adversarial Attack in Time Series Classification

Revisiting Min-Max Optimization Problem in Adversarial Training

A Grey-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse

Towards Efficient Formal Verification of Spiking Neural Network

Adversarial Attack for Explanation Robustness of Rationalization Models

Security Assessment of Hierarchical Federated Deep Learning

MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification

Privacy-preserving Universal Adversarial Defense for Black-box Models

Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks

Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis

Regularization for Adversarial Robust Learning