paper-with-me

홈 › Papers

Support is All You Need for Certified VAE Training

2025-04-16 · Changming Xu, Debangshu Banerjee, Deepak Vasisht, Gagandeep Singh

Variational Autoencoders (VAEs) have become increasingly popular and deployed in safety-critical applications. In such applications, we want to give certified probabilistic guarantees on performance under adversarial attacks. We propose a novel method, CIVET, for certified training of VAEs. CIVET depends on the key insight that we can bound worst-case VAE error by bounding the error on carefully chosen support sets at the latent layer. We show this point mathematically and present a novel training algorithm utilizing this insight. We show in an extensive evaluation across different datasets (in both the wireless and vision application areas), architectures, and perturbation magnitudes that our method outperforms SOTA methods achieving good standard performance with strong robustness guarantees.

📄 PDF Abstract BibTeX arXiv:2504.11831

Code (0)

등록된 구현이 없습니다.

Tasks

All

Similar Papers 제목 키워드 기반

Certified Training: Small Boxes are All You Need

2022-10-10 · Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin Vechev

To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key insight that propagating interval bounds fo…

Adversarial RobustnessAll

How robust accuracy suffers from certified training with convex relaxations

2023-06-12 · Piersilvio De Bartolomeis, Jacob Clarysse, Amartya Sanyal, Fanny Yang

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences…

Certified Adversarial Robustness Under the Bounded Support Set

2021-09-29 · Yiwen Kou, Qinyuan Zheng, Yisen Wang

Deep neural networks (DNNs) have revealed severe vulnerability to adversarial perturbations, beside empirical adversarial training for robustness, the design of provably robust classifiers attracts more and more attentio…

Adversarial Robustness

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

2020-02-28 · NeurIPS 2020 12 · Kaidi Xu, Zhouxing Shi, huan zhang, Yihan Wang 외

Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness v…

Quantization

Fast Certified Robust Training with Short Warmup

2021-03-31 · NeurIPS 2021 12 · Zhouxing Shi, Yihan Wang, huan zhang, JinFeng Yi 외

Recently, bound propagation based certified robust training methods have been proposed for training neural networks with certifiable robustness guarantees. Despite that state-of-the-art (SOTA) methods including interval …

Adversarial Defense