Support is All You Need for Certified VAE Training
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.
Code (0)
등록된 구현이 없습니다.
Tasks
AllSimilar Papers 제목 키워드 기반
Certified Training: Small Boxes are All You Need
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 RobustnessAllHow robust accuracy suffers from certified training with convex relaxations
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
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 RobustnessAutomatic Perturbation Analysis for Scalable Certified Robustness and Beyond
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…
QuantizationFast Certified Robust Training with Short Warmup
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