Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach
Hangyu Liu, Bo Peng, Pengxiang Ding, Donglin Wang
Abstract
Compared to single-target adversarial attacks, multi-target attacks have garnered significant attention due to their ability to generate adversarial images for multiple target classes simultaneously. However, existing generative approaches for multi-target attacks primarily encode target labels into one-dimensional tensors, leading to a loss of fine-grained visual information and overfitting to model-specific features during noise generation. To address this gap, we first identify and validate that the semantic feature quality and quantity are critical factors affecting the transferability of targeted attacks: 1) Feature quality refers to the structural and detailed completeness of the implanted target features, as deficiencies may result in the loss of key discriminative information; 2) Feature quantity refers to the spatial sufficiency of the implanted target features, as inadequacy limits the victim model
BibTeX
@inproceedings{aaai2026_rethinkingtarget,
title = {Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach},
author = {Hangyu Liu and Bo Peng and Pengxiang Ding and Donglin Wang},
booktitle = {AAAI 2026},
year = {2026}
}