中文
相关论文

相关论文: Debona: Decoupled Boundary Network Analysis for Ti…

200 篇论文

A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. Previous methods have either used off-the-shelf solvers, discarding the problem structure, or relaxed the problem even…

This paper addresses the problem of formally verifying desirable properties of neural networks, i.e., obtaining provable guarantees that neural networks satisfy specifications relating their inputs and outputs (robustness to bounded norm…

机器学习 · 计算机科学 2018-08-06 Krishnamurthy , Dvijotham , Robert Stanforth , Sven Gowal , Timothy Mann , Pushmeet Kohli

Neural networks (NNs) are now routinely implemented on systems that must operate in uncertain environments, but the tools for formally analyzing how this uncertainty propagates to NN outputs are not yet commonplace. Computing tight bounds…

机器学习 · 计算机科学 2020-12-08 Michael Everett , Golnaz Habibi , Jonathan P. How

Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable their deployment in safety-critical applications. This paper…

最优化与控制 · 数学 2024-04-02 Haoruo Zhao , Hassan Hijazi , Haydn Jones , Juston Moore , Mathieu Tanneau , Pascal Van Hentenryck

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated…

机器学习 · 计算机科学 2021-10-27 Mike Wu , Noah Goodman , Stefano Ermon

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…

机器学习 · 计算机科学 2026-02-06 Wenting Li , Saif R. Kazi , Russell Bent , Duo Zhou , Huan Zhang

Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control. Although these networks involve the composition of simple arithmetic operations, it can be very challenging…

Verification of deep neural networks has witnessed a recent surge of interest, fueled by success stories in diverse domains and by abreast concerns about safety and security in envisaged applications. Complexity and sheer size of such…

机器学习 · 计算机科学 2020-03-18 Dario Guidotti , Francesco Leofante , Luca Pulina , Armando Tacchella

Many available formal verification methods have been shown to be instances of a unified Branch-and-Bound (BaB) formulation. We propose a novel machine learning framework that can be used for designing an effective branching strategy as well…

机器学习 · 计算机科学 2021-07-28 Florian Jaeckle , Jingyue Lu , M. Pawan Kumar

Neural networks are not learning optimal decision boundaries. We show that decision boundaries are situated in areas of low training data density. They are impacted by few training samples which can easily lead to overfitting. We provide a…

机器学习 · 计算机科学 2023-10-09 Johannes Schneider

Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that…

机器学习 · 计算机科学 2019-02-19 Vincent Tjeng , Kai Xiao , Russ Tedrake

With the increasing application of deep learning in mission-critical systems, there is a growing need to obtain formal guarantees about the behaviors of neural networks. Indeed, many approaches for verifying neural networks have been…

机器学习 · 计算机科学 2022-08-17 Tom Zelazny , Haoze Wu , Clark Barrett , Guy Katz

Neural networks have been widely applied in security applications such as spam and phishing detection, intrusion prevention, and malware detection. This black-box method, however, often has uncertainty and poor explainability in…

密码学与安全 · 计算机科学 2022-10-12 Mark Huasong Meng , Guangdong Bai , Sin Gee Teo , Zhe Hou , Yan Xiao , Yun Lin , Jin Song Dong

Neural networks are increasingly deployed in real-world safety-critical domains such as autonomous driving, aircraft collision avoidance, and malware detection. However, these networks have been shown to often mispredict on inputs with…

机器学习 · 计算机科学 2018-11-09 Shiqi Wang , Kexin Pei , Justin Whitehouse , Junfeng Yang , Suman Jana

Although neural networks are widely used, it remains challenging to formally verify the safety and robustness of neural networks in real-world applications. Existing methods are designed to verify the network before deployment, which are…

机器学习 · 计算机科学 2023-02-06 Tianhao Wei , Changliu Liu

Machine learning techniques are immensely deployed in both industry and academy. Recent studies indicate that machine learning models used for classification tasks are vulnerable to adversarial examples, which limits the usage of…

计算机视觉与模式识别 · 计算机科学 2020-07-14 Yutong Gao , Yi Pan

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…

机器学习 · 计算机科学 2024-03-19 Suhas Kotha , Christopher Brix , Zico Kolter , Krishnamurthy Dvijotham , Huan Zhang

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…

计算机视觉与模式识别 · 计算机科学 2021-01-13 Hanwei Zhang , Yannis Avrithis , Teddy Furon , Laurent Amsaleg

As deep neural networks (DNNs) are increasingly used in safety-critical applications, there is a growing concern for their reliability. Even highly trained, high-performant networks are not 100% accurate. However, it is very difficult to…

神经与进化计算 · 计算机科学 2024-07-30 Eduard Pinconschi , Divya Gopinath , Rui Abreu , Corina S. Pasareanu

Deep learning models have been the subject of study from various perspectives, for example, their training process, interpretation, generalization error, robustness to adversarial attacks, etc. A trained model is defined by its decision…

机器学习 · 计算机科学 2019-08-09 Roozbeh Yousefzadeh , Dianne P O'Leary
‹ 上一页 1 2 3 10 下一页 ›