Dataset for "Trading Depth for Diversity: Boosting Adversarial Transferability via Sequential Multi-Path Optimization"

Read full text Summarise with VIRAT
Authors: zbc123 zhang
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This dataset contains the selected image list, raw experimental results, supplementary visualizations, and representative adversarial examples used in the study titled "Boosting Adversarial Transferability via Multi-Path Gradient Ascent". The clean images were selected from the ImageNet validation set. This record provides the materials supporting the conclusions reported in the manuscript.

Fields of Study & Subjects

Adversarial Robustness in Machine Learning Digital Media Forensic Detection Generative Adversarial Networks and Image Synthesis

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN
Document type
Dataset