In this work, we present an early prototype of NeVer 2.0, a new system for automated synthesis and analysis of deep neural networks.NeVer 2.0borrows its design philosophy from NeVer, the first package that integrated learning, automated verification and repair of (shallow) neural networks in a single tool. The goal of NeVer 2.0 is to provide a similar integration for deep networks by leveraging a selection of state-of-the-art learning frameworks and integrating them with verification algorithms to ease the scalability challenge and make repair of faulty networks possible.
Zhejiang University（浙江大学）；Singapore Management University（新加坡管理大学）；Huawei International Pte Ltd（华为国际有限公司）
Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification techniques have been proposed to tackle the correctness problem of neural networks, it is possible that static verification may never be sufficiently scalable to handle real-world neural networks. In this work, we propose a runtime verification method to ensure the correctness of neural networks. Given a neural network and a desirable safety property, we adopt sta…
University of Massachusetts（马萨诸塞大学）；Google, Inc.（谷歌公司）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Formally verifying software properties is a highly desirable but labor-intensive task. Recent work has developed methods to automate formal verification using proof assistants, such as Coq and Isabelle/HOL, e.g., by training a model to predict one proof step at a time, and using that model to search through the space of possible proofs. This paper introduces a new method to automate formal verification: We use large language models, trained on natural language text and code and fine-tuned on proofs, to generate whole proofs for theorems at once, rather than one step at a time. We combine this …
Deep neural networks (DNNs) have become increasingly popular in recent years. However, despite their many successes, DNNs may also err and produce incorrect and potentially fatal outputs in safety-critical settings, such as autonomous driving, medical diagnosis, and airborne collision avoidance systems. Much work has been put into detecting such erroneous behavior in DNNs, e.g., via testing or verification, but removing these errors after their detection has received lesser attention. We present here a new tool, called 3M-DNN, for repairing a given DNN, which is known to err on some set of inp…
Repairing Deep Neural Networks Based on Behavior Imitation
National University of Defense Technology（国防科技大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Patch Synthesis for Property Repair of Deep Neural Networks
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；School of Cyberspace, Hangzhou Dianzi University（杭州电子科技大学网络空间学院）；Zhejiang University（浙江大学）；College of Computer and Information Science, Software College, Southwest University（西南大学计算机与信息科学学院、软件学院）；Nanjing Institute of Software Technology, Chinese Academy of Sciences（中国科学院南京软件技术研究所）；University of Liverpool（利物浦大学）
Over the last decade, Neural Networks (NNs) have been widely used in numerous applications including safety-critical ones such as autonomous systems. Despite their emerging adoption, it is well known that NNs are susceptible to Adversarial Attacks. Hence, it is highly important to provide guarantees that such systems work correctly. To remedy these issues we introduce a framework for repairing unsafe NNs w.r.t. safety specification, that is by utilizing satisfiability modulo theories (SMT) solvers. Our method is able to search for a new, safe NN representation, by modifying only a few of its w…
There has been significant recent interest in devising verification techniques for learning-enabled controllers (LECs) that manage safety-critical systems. Given the opacity and lack of interpretability of the neural policies that govern the behavior of such controllers, many existing approaches enforce safety properties through shield, a dynamic monitoring-and-repairing mechanism that ensures a LEC does not emit actions that would violate desired safety conditions. These methods, however, have been shown to have significant scalability limitations because verification costs grow as problem di…
