cs.AI updates on arXiv.org 19小时前
Crafting Imperceptible On-Manifold Adversarial Attacks for Tabular Data
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

提出基于混合输入VAE的潜在空间扰动框架,生成难以察觉的对抗样本,在表格数据上实现更低的异常率和更一致的性能。

arXiv:2507.10998v1 Announce Type: cross Abstract: Adversarial attacks on tabular data present fundamental challenges distinct from image or text domains due to the heterogeneous nature of mixed categorical and numerical features. Unlike images where pixel perturbations maintain visual similarity, tabular data lacks intuitive similarity metrics, making it difficult to define imperceptible modifications. Additionally, traditional gradient-based methods prioritise $\ell_p$-norm constraints, often producing adversarial examples that deviate from the original data distributions, making them detectable. We propose a latent space perturbation framework using a mixed-input Variational Autoencoder (VAE) to generate imperceptible adversarial examples. The proposed VAE integrates categorical embeddings and numerical features into a unified latent manifold, enabling perturbations that preserve statistical consistency. We specify In-Distribution Success Rate (IDSR) to measure the proportion of adversarial examples that remain statistically indistinguishable from the input distribution. Evaluation across six publicly available datasets and three model architectures demonstrates that our method achieves substantially lower outlier rates and more consistent performance compared to traditional input-space attacks and other VAE-based methods adapted from image domain approaches. Our comprehensive analysis includes hyperparameter sensitivity, sparsity control mechanisms, and generative architectural comparisons, revealing that VAE-based attacks depend critically on reconstruction quality but offer superior practical utility when sufficient training data is available. This work highlights the importance of on-manifold perturbations for realistic adversarial attacks on tabular data, offering a robust approach for practical deployment. The source code can be accessed through https://github.com/ZhipengHe/VAE-TabAttack.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

表格数据 对抗攻击 VAE
相关文章