paper-with-me

홈 › Papers

Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models

2019-06-03 · Paweł Morawiecki, Przemysław Spurek, Marek Śmieja, Jacek Tabor

We present an efficient technique, which allows to train classification networks which are verifiably robust against norm-bounded adversarial attacks. This framework is built upon the work of Gowal et al., who applies the interval arithmetic to bound the activations at each layer and keeps the prediction invariant to the input perturbation. While that method is faster than competitive approaches, it requires careful tuning of hyper-parameters and a large number of epochs to converge. To speed up and stabilize training, we supply the cost function with an additional term, which encourages the model to keep the interval bounds at hidden layers small. Experimental results demonstrate that we can achieve comparable (or even better) results using a smaller number of training iterations, in a more stable fashion. Moreover, the proposed model is not so sensitive to the exact specification of the training process, which makes it easier to use by practitioners.

📄 PDF Abstract BibTeX arXiv:1906.00628

Code (1)

pawelmorawiecki/Fast-and-stable-IBP pytorch

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

2019-06-14 · ICLR 2020 1 · Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal 외

Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training …

Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation

2021-09-29 · ICLR 2022 4 · Colin Wei, J Zico Kolter

Deep equilibrium layers (DEQs) have demonstrated promising performance and are competitive with standard explicit models on many benchmarks. However, little is known about certifying robustness for these models. Inspired…

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…

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

BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic

2022-11-22 · Wael Fatnassi, Haitham Khedr, Valen Yamamoto, Yasser Shoukry

In this paper, we present BERN-NN as an efficient tool to perform bound propagation of Neural Networks (NNs). Bound propagation is a critical step in wide range of NN model checkers and reachability analysis tools. Given…