中文
相关论文

相关论文: Unifying Qualitative and Quantitative Safety Verif…

200 篇论文

Deep Neural Networks are increasingly adopted in critical tasks that require a high level of safety, e.g., autonomous driving. While state-of-the-art verifiers can be employed to check whether a DNN is unsafe w.r.t. some given property…

人工智能 · 计算机科学 2023-06-21 Luca Marzari , Davide Corsi , Ferdinando Cicalese , Alessandro Farinelli

Machine learning techniques often lack formal correctness guarantees, evidenced by the widespread adversarial examples that plague most deep-learning applications. This lack of formal guarantees resulted in several research efforts that aim…

机器学习 · 计算机科学 2024-06-11 Anahita Baninajjar , Ahmed Rezine , Amir Aminifar

Traditional methods for formal verification (FV) of deep neural networks (DNNs) are constrained by a binary encoding of safety properties, where a model is classified as either safe or unsafe (robust or not robust). This binary encoding…

人工智能 · 计算机科学 2025-05-09 Luca Marzari , Isabella Mastroeni , Alessandro Farinelli

Deep neural networks (DNNs) are increasingly being employed in safety-critical systems, and there is an urgent need to guarantee their correctness. Consequently, the verification community has devised multiple techniques and tools for…

计算机科学中的逻辑 · 计算机科学 2022-08-30 Omri Isac , Clark Barrett , Min Zhang , Guy Katz

Deep Neural Networks (DNNs) are powerful tools that have shown extraordinary results in many scenarios, ranging from pattern recognition to complex robotic problems. However, their intricate designs and lack of transparency raise safety…

人工智能 · 计算机科学 2023-12-12 Luca Marzari , Gabriele Roncolato , Alessandro Farinelli

Despite the functional success of deep neural networks (DNNs), their trustworthiness remains a crucial open challenge. To address this challenge, both testing and verification techniques have been proposed. But these existing techniques…

机器学习 · 计算机科学 2021-03-24 Teodora Baluta , Zheng Leong Chua , Kuldeep S. Meel , Prateek Saxena

Deep Neural Networks (DNN) have improved the quality of several non-safety related products in the past years. However, before DNNs should be deployed to safety-critical applications, their robustness needs to be systematically analyzed. A…

Recent advances in Deep Machine Learning have shown promise in solving complex perception and control loops via methods such as reinforcement and imitation learning. However, guaranteeing safety for such learned deep policies has been a…

机器人学 · 计算机科学 2020-03-03 Tom Hirshberg , Sai Vemprala , Ashish Kapoor

Deep neural networks (DNNs) have become the technology of choice for realizing a variety of complex tasks. However, as highlighted by many recent studies, even an imperceptible perturbation to a correctly classified input can lead to…

机器学习 · 计算机科学 2022-07-27 Guy Amir , Tom Zelazny , Guy Katz , Michael Schapira

The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. Despite the reputation of learned NN models to behave as black boxes and…

人工智能 · 计算机科学 2018-05-23 Rudy Bunel , Ilker Turkaslan , Philip H. S. Torr , Pushmeet Kohli , M. Pawan Kumar

Neural networks have emerged as essential components in safety-critical applications -- these use cases demand complex, yet trustworthy computations. Binarized Neural Networks (BNNs) are a type of neural network where each neuron is…

机器学习 · 计算机科学 2025-07-08 Jiong Yang , Yong Kiam Tan , Mate Soos , Magnus O. Myreen , Kuldeep S. Meel

Neural networks are increasingly employed in safety-critical domains. This has prompted interest in verifying or certifying logically encoded properties of neural networks. Prior work has largely focused on checking existential properties,…

密码学与安全 · 计算机科学 2019-06-26 Teodora Baluta , Shiqi Shen , Shweta Shinde , Kuldeep S. Meel , Prateek Saxena

Learning-based methods could provide solutions to many of the long-standing challenges in control. However, the neural networks (NNs) commonly used in modern learning approaches present substantial challenges for analyzing the resulting…

机器学习 · 计算机科学 2022-02-03 Michael Everett

Despite the tremendous advances that have been made in the last decade on developing useful machine-learning applications, their wider adoption has been hindered by the lack of strong assurance guarantees that can be made about their…

机器学习 · 计算机科学 2019-07-18 He Zhu , Zikang Xiong , Stephen Magill , Suresh Jagannathan

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…

机器学习 · 计算机科学 2023-04-13 Linyi Li , Tao Xie , Bo Li

Deep neural networks (DNNs) enable high performance across domains but remain vulnerable to adversarial perturbations, limiting their use in safety-critical settings. Here, we introduce two quantum-optimization-based models for robust…

机器学习 · 计算机科学 2026-03-03 Wenxin Li , Wenchao Liu , Chuan Wang , Qi Gao , Yin Ma , Hai Wei , Kai Wen

We provide a novel approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier…

系统与控制 · 电气工程与系统科学 2020-09-22 Hengjun Zhao , Xia Zeng , Taolue Chen , Zhiming Liu , Jim Woodcock

Software development in the aerospace domain requires adhering to strict, high-quality standards. While there exist regulatory guidelines for commercial software in this domain (e.g., ARP-4754 and DO-178), these do not apply to software…

软件工程 · 计算机科学 2024-08-06 Guy Katz , Natan Levy , Idan Refaeli , Raz Yerushalmi

Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications. In this paper, we study verification problems for Binarized Neural Networks…

机器学习 · 计算机科学 2021-03-15 Yedi Zhang , Zhe Zhao , Guangke Chen , Fu Song , Taolue Chen

Deep Neural Networks (DNNs) have become key components of many safety-critical applications such as autonomous driving and medical diagnosis. However, DNNs have been shown suffering from poor robustness because of their susceptibility to…

机器学习 · 计算机科学 2020-07-28 Wenjie Wan , Zhaodi Zhang , Yiwei Zhu , Min Zhang , Fu Song
‹ 上一页 1 2 3 10 下一页 ›