English
Related papers

Related papers: Towards Evaluating and Training Verifiably Robust …

200 papers

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 by a factor of…

Machine Learning · Computer Science 2019-11-28 Huan Zhang , Hongge Chen , Chaowei Xiao , Sven Gowal , Robert Stanforth , Bo Li , Duane Boning , Cho-Jui Hsieh

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…

As robustness verification methods are becoming more precise, training certifiably robust neural networks is becoming ever more relevant. To this end, certified training methods compute and then optimize an upper bound on the worst-case…

Machine Learning · Computer Science 2024-02-29 Yuhao Mao , Mark Niklas Müller , Marc Fischer , Martin Vechev

Interval Bound Propagation (IBP) is so far the base of state-of-the-art methods for training neural networks with certifiable robustness guarantees when potential adversarial perturbations present, while the convergence of IBP training…

Machine Learning · Computer Science 2022-03-18 Yihan Wang , Zhouxing Shi , Quanquan Gu , Cho-Jui Hsieh

In various scenarios motivated by real life, such as medical data analysis, autonomous driving, and adversarial training, we are interested in robust deep networks. A network is robust when a relatively small perturbation of the input…

Machine Learning · Computer Science 2024-10-07 Patryk Krukowski , Daniel Wilczak , Jacek Tabor , Anna Bielawska , Przemysław Spurek

Bound propagation based incomplete neural network verifiers such as CROWN are very efficient and can significantly accelerate branch-and-bound (BaB) based complete verification of neural networks. However, bound propagation cannot fully…

Machine Learning · Computer Science 2021-11-02 Shiqi Wang , Huan Zhang , Kaidi Xu , Xue Lin , Suman Jana , Cho-Jui Hsieh , J. Zico Kolter

Recent works have tried to increase the verifiability of adversarially trained networks by running the attacks over domains larger than the original perturbations and adding various regularization terms to the objective. However, these…

Machine Learning · Computer Science 2023-06-01 Alessandro De Palma , Rudy Bunel , Krishnamurthy Dvijotham , M. Pawan Kumar , Robert Stanforth

Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a nominal input). However, many use cases of neural network…

Machine Learning · Computer Science 2024-03-19 Suhas Kotha , Christopher Brix , Zico Kolter , Krishnamurthy Dvijotham , Huan Zhang

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 bound propagation…

Machine Learning · Computer Science 2021-10-29 Zhouxing Shi , Yihan Wang , Huan Zhang , Jinfeng Yi , Cho-Jui Hsieh

Training Deep Neural Networks that are robust to norm bounded adversarial attacks remains an elusive problem. While exact and inexact verification-based methods are generally too expensive to train large networks, it was demonstrated that…

Machine Learning · Computer Science 2021-06-15 Salman Alsubaihi , Adel Bibi , Modar Alfadly , Abdullah Hamdi , Bernard Ghanem

The rapid growth of deep learning applications in real life is accompanied by severe safety concerns. To mitigate this uneasy phenomenon, much research has been done providing reliable evaluations of the fragility level in different deep…

Machine Learning · Computer Science 2019-12-03 Zhaoyang Lyu , Ching-Yun Ko , Zhifeng Kong , Ngai Wong , Dahua Lin , Luca Daniel

Neural network verifiers based on linear bound propagation scale impressively to massive models but can be surprisingly loose when neuron coupling is crucial. Conversely, semidefinite programming (SDP) verifiers capture inter-neuron…

Machine Learning · Computer Science 2025-06-10 Hong-Ming Chiu , Hao Chen , Huan Zhang , Richard Y. Zhang

Finding minimum distortion of adversarial examples and thus certifying robustness in neural network classifiers for given data points is known to be a challenging problem. Nevertheless, recently it has been shown to be possible to give a…

Machine Learning · Computer Science 2018-11-05 Huan Zhang , Tsui-Wei Weng , Pin-Yu Chen , Cho-Jui Hsieh , Luca Daniel

Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to partially mitigate such…

Computation and Language · Computer Science 2019-12-23 Po-Sen Huang , Robert Stanforth , Johannes Welbl , Chris Dyer , Dani Yogatama , Sven Gowal , Krishnamurthy Dvijotham , Pushmeet Kohli

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschitz constant.…

Machine Learning · Computer Science 2021-11-03 Yujia Huang , Huan Zhang , Yuanyuan Shi , J Zico Kolter , Anima Anandkumar

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…

Machine Learning · Computer Science 2019-07-04 Paweł Morawiecki , Przemysław Spurek , Marek Śmieja , Jacek Tabor

As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical applications, the security concerns in SNNs attract more attention. Currently, researchers have already demonstrated an SNN can be attacked with…

Neural and Evolutionary Computing · Computer Science 2022-05-04 Ling Liang , Kaidi Xu , Xing Hu , Lei Deng , Yuan Xie

With the rapid development of deep learning, the sizes of neural networks become larger and larger so that the training and inference often overwhelm the hardware resources. Given the fact that neural networks are often over-parameterized,…

Machine Learning · Computer Science 2022-06-20 Zhangheng Li , Tianlong Chen , Linyi Li , Bo Li , Zhangyang Wang

Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalability-completeness…

Machine Learning · Computer Science 2026-02-06 Wenting Li , Saif R. Kazi , Russell Bent , Duo Zhou , Huan Zhang

Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robustness, and safety. However, existing works cannot handle…

Machine Learning · Computer Science 2022-12-06 Huan Zhang , Shiqi Wang , Kaidi Xu , Linyi Li , Bo Li , Suman Jana , Cho-Jui Hsieh , J. Zico Kolter
‹ Prev 1 2 3 10 Next ›