paper-with-me

홈 › Papers

Scalable Verified Training for Provably Robust Image Classification

2019-10-01 · ICCV 2019 10 · Sven Gowal, Krishnamurthy (Dj) Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Mann, Pushmeet Kohli

Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all possible adversarial perturbations. While these techniques show promise, they often result in difficult optimization procedures that remain hard to scale to larger networks. Through a comprehensive analysis, we show how a simple bounding technique, interval bound propagation (IBP), can be exploited to train large provably robust neural networks that beat the state-of-the-art in verified accuracy. While the upper bound computed by IBP can be quite weak for general networks, we demonstrate that an appropriate loss and clever hyper-parameter schedule allow the network to adapt such that the IBP bound is tight. This results in a fast and stable learning algorithm that outperforms more sophisticated methods and achieves state-of-the-art results on MNIST, CIFAR-10 and SVHN. It also allows us to train the largest model to be verified beyond vacuous bounds on a downscaled version of IMAGENET.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise

2017-11-20 · CVPR 2018 6 · Kuang-Huei Lee, Xiaodong He, Lei Zhang, Linjun Yang

In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect lab…

ClassificationGeneral Classificationimage-classificationImage Classification+1

Scalable Neural Learning for Verifiable Consistency with Temporal Specifications

2019-09-25 · Sumanth Dathathri, Johannes Welbl, Krishnamurthy (Dj) Dvijotham, Ramana Kumar 외

Formal verification of machine learning models has attracted attention recently, and significant progress has been made on proving simple properties like robustness to small perturbations of the input features. In this c…

Adversarial RobustnessLanguage ModelingLanguage Modelling

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts

2024-05-26 · Mohammed Nowaz Rabbani Chowdhury, Meng Wang, Kaoutar El Maghraoui, Naigang Wang 외

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but…

Binary ClassificationMixture-of-Experts

Boosting Verified Training for Robust Image Classifications via Abstraction

2023-03-21 · CVPR 2023 1 · Zhaodi Zhang, Zhiyi Xue, Yang Chen, Si Liu 외

This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By…

On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models

2018-10-30 · Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel 외

Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case l…