In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typically apply formal verification \emph{after} the controller has been learned, it is sometimes difficult to obtain any certificate, even after many iterations between learning and verification. To address this challenge, we propose a framework that jointly conducts reinforcement learning and formal verification by formulating and solving a novel bilevel optimization problem, which is differentiable by the gradients from the value function and certificates. Experiments on a variety of examples demonstrate the significant advantages of our framework over the model-based stochastic value gradient (SVG) method and the model-free proximal policy optimization (PPO) method in finding feasible controllers with barrier functions and Lyapunov functions that ensure system safety and stability.
Neural Ordinary Differential Equations (NODEs) are a novel neural architecture, built around initial value problems with learned dynamics which are solved during inference. Thought to be inherently more robust against adversarial perturbations, they were recently shown to be vulnerable to strong adversarial attacks, highlighting the need for formal guarantees. However, despite significant progress in robustness verification for standard feed-forward architectures, the verification of high dimensional NODEs remains an open problem. In this work, we address this challenge and propose GAINS, an a…
Certified Neural Approximations of Nonlinear Dynamics
Delft Center for Systems and Control（代尔夫特系统与控制中心）；Department of Computer Science, University of Oxford（牛津大学计算机科学系）；The Italian Institute of Artificial Intelligence (AI4I)（意大利人工智能研究所（AI4I））
CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks
Department of Computer Science, Florida State University, Tallahassee, Florida, United States（佛罗里达州立大学计算机科学系）；Department of Mathematics, University of Wisconsin, Madison, Wisconsin, United States（威斯康星大学麦迪逊分校数学系）；Department of Computer Science, Duke University, Durham, North Carolina, United States（杜克大学计算机科学系）；Department of Statistics and Operations Research, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, United States（北卡罗来纳大学教堂山分校统计与运筹学系）
CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration
School of Control and Computer Engineering, North China Electric Power University（控制与计算机工程学院，华北电力大学）；College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）；School of Cybersecurity, Northwestern Polytechnical University（网络安全学院，西北工业大学）；Department of Computer Science, University of Maryland（计算机科学系，马里兰大学）；Alibaba Group（阿里巴巴集团）
Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
Generative AI Lab, College of Computing；Data Science, Nanyang Technological University, Singapore；Department of Computer Science；Engineering, Texas A\&M University, USA
GeoCert: Certified Geometric AI for Reliable Forecasting
Department of Biomedical Informatics & Data Science, Yale University（耶鲁大学生物医学信息学与数据科学系）；Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）；School of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系）
The rising popularity of neural networks (NNs) in recent years and their increasing prevalence in real-world applications have drawn attention to the importance of their verification. While verification is known to be computationally difficult theoretically, many techniques have been proposed for solving it in practice. It has been observed in the literature that by default neural networks rarely satisfy logical constraints that we want to verify. A good course of action is to train the given NN to satisfy said constraint prior to verifying them. This idea is sometimes referred to as continuou…
Efficient Certified Reasoning for Binarized Neural Networks
Georgia Institute of Technology（佐治亚理工学院）；United States Institute for Infocomm Research (I 2 R)（美国信息与通信研究所）；Nanyang Technological University（南洋理工大学）；University of Toronto（多伦多大学）；Chalmers University of Technology（楚克大学）；University of Gothenburg（哥德堡大学）
In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with similar approaches, we do not extract the embedding of an utterance from the mean reduction of the temporal dimension. Our system replaces the mean by a phrase alignment model to keep the temporal structure of each phrase which is relevant in this application since the phonetic information is part of the identity in the verification task. Moreover, we can apply a …
University of Washington（华盛顿大学）；Amazon, Alexa AI（亚马逊Alexa人工智能部门）；University of Toronto（多伦多大学）；Facebook（脸书）
Optimal selection of a subset of items from a given set is a hard problem that requires combinatorial optimization. In this paper, we propose a subset selection algorithm that is trainable with gradient-based methods yet achieves near-optimal performance via submodular optimization. We focus on the task of identifying a relevant set of sentences for claim verification in the context of the FEVER task. Conventional methods for this task look at sentences on their individual merit and thus do not optimize the informativeness of sentences as a set. We show that our proposed method which builds on…
Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Shenzhen Research Institute, Nanjing University（南京大学深圳研究院）
