Adversarial Transferability And Beyond

Adversarial Transferability and Beyond

Deep Neural Networks have achieved great success in various vision tasks in recent years. However, they remain vulnerable to ...

Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differen

Authors: Waseda, Futa Kai*; Nishikawa, Sosuke; Le, Trung-Nghia; Nguyen, Huy Hong; Echizen, Isao Description: Deep neural ...

Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation

This document explores

NDSS 2024 - Enhance Stealthiness and Transferability of Adversarial Attacks with Class Activation Ma

SESSION 13B-4 Enhance Stealthiness and

Boosting the Transferability of Adversarial Samples via Attention

Authors: Weibin Wu, Yuxin Su, Xixian Chen, Shenglin Zhao, Irwin King, Michael R. Lyu, Yu-Wing Tai Description: The widespread ...

An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability

An Adaptive Model Ensemble

[ICCV 2025] Boosting Adversarial Transferability via Residual Perturbation Attack

Efficient Adversarial Training With Transferable Adversarial Examples

Authors: Haizhong Zheng, Ziqi Zhang, Juncheng Gu, Honglak Lee, Atul Prakash Description:

USENIX Security '24 - Transferability of White-box Perturbations: Query-Efficient Adversarial...

Transferability

Improving the Transferability of Adversarial Samples by Path-Augmented Method

CVPR 2023.

Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropout

Adversarial Attacks

Find out how to fool a neural network. 00:00 Introduction 02:29 Classification Loss 08:19

Enhancing Cross-Task Black-Box Transferability of Adversarial Examples With Dispersion Reduction

Authors: Yantao Lu, Yunhan Jia, Jianyu Wang, Bai Li, Weiheng Chai, Lawrence Carin, Senem Velipasalar Description: Neural ...

CVPR 2023 - StyLess: Boosting the Transferability of Adversarial Examples

Hey there! This is our presentation for our paper at CVPR 2023 called: "StyLess: Boosting the

Adversarial Machine Learning and Beyond - Philipp Benz and Chaoning Zhang

This talk will introduce

Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification...

Authors: Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin Description: The success of DNNs has driven the ...

Universal and Transferable LLM Attacks - A New Threat to AI Safety

In this video we review the paper Universal and

Lecture 16 | Adversarial Examples and Adversarial Training

In Lecture 16, guest lecturer Ian Goodfellow discusses

Beyond "provable" robustness: new directions in adversarial robustness

ICLR 2020 Towards Trustworthy ML Workshop Talk.

USENIX Security '19 - Why Do Adversarial Attacks Transfer? Explaining Transferability of

Why Do