While adversarial robustness in computer vision is a mature research field, fewer researchers have tackled the evasion attacks against tabular deep learning, and even fewer investigated robustification mechanisms and reliable defenses. We hypothesize that this lag in the research on tabular adversarial attacks is in part due to the lack of standardized benchmarks. To fill this gap, we propose TabularBench, the first comprehensive benchmark of robustness of tabular deep learning classification models. We evaluated adversarial robustness with CAA, an ensemble of gradient and search attacks which was recently demonstrated as the most effective attack against a tabular model. In addition to our open benchmark (https://github.com/serval-uni-lu/tabularbench) where we welcome submissions of new models and defenses, we implement 7 robustification mechanisms inspired by state-of-the-art defenses in computer vision and propose the largest benchmark of robust tabular deep learning over 200 models across five critical scenarios in finance, healthcare and security. We curated real datasets for each use case, augmented with hundreds of thousands of realistic synthetic inputs, and trained and assessed our models with and without data augmentations. We open-source our library that provides API access to all our pre-trained robust tabular models, and the largest datasets of real and synthetic tabular inputs. Finally, we analyze the impact of various defenses on the robustness and provide actionable insights to design new defenses and robustification mechanisms.
Towards Benchmarking Foundation Models for Tabular Data With Text
Department of Computer Science, University of Freiburg, Freiburg, Germany(弗赖堡大学计算机科学系);Prior Labs, Freiburg, Germany(Prior实验室);ELLIS Institute, Tubingen, Germany(图宾根ELLIS研究所)
STRABLE: Benchmarking Tabular Machine Learning with Strings
SODA Team, INRIA Saclay(SODA团队,INRIA萨克莱实验室);Probabl;University of Freiburg(弗赖堡大学);Prior Labs;ELLIS Institute Tübingen(图宾根ELLIS研究所);Technion – Israel Institute of Technology(技术ion-以色列理工学院)
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Technion – Israel Institute of Technology(技术ion – 以色列理工学院);Prior Labs(Prior实验室);NVIDIA;SODA Team, INRIA Saclay, Palaiseau(SODA团队,INRIA萨克莱,帕莱索);University of Freiburg(弗赖堡大学);Probabl;ELLIS Institute Tübingen(图宾根ELLIS研究所)
Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs
Department of Intensive Care and Neonatology and Children’s Research Center University of Zurich University Children’s Hospital Zurich(重症护理与新生儿科及儿童研究中心,苏黎世大学苏黎世儿童医院);Department of Health Sciences and Technology ETH Zurich(健康科学与技术系,苏黎世联邦理工学院);Department of Computer Science ETH Zurich(计算机科学系,苏黎世联邦理工学院)
Benchmarking Tabular Foundation Models for Conditional Density Estimation in Regression
Department of Statistics, Federal University of São Carlos (UFSCar)(圣卡洛斯联邦大学统计系);Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK(格勒诺布尔阿尔卑斯大学、法国国家信息与自动化研究所、法国国家科学研究中心、格勒诺布尔国立理工学院、让·库尔坦数学实验室)
ConvGeN: Convex space learning improves deep-generative oversampling for tabular imbalanced classification on smaller datasets
University of Rostock(罗斯托克大学);Leibniz-Institute for Food Systems Biology(莱布尼茨食品系统生物学研究所);Technical University of Munich(慕尼黑工业大学);Technische Universität Dresden(德累斯顿工业大学)
SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data
Université du Littoral-Côte-d’Opale(滨海-加来海峡大学);University of Freiburg(弗莱堡大学);Prior Labs(Prior实验室);HTW Berlin(柏林应用科学大学);ELLIS Institute Tübingen(ELLIS蒂宾根研究所)
TabArena: A Living Benchmark for Machine Learning on Tabular Data
Amazon Web Services(亚马逊网络服务);University of Freiburg(弗赖堡大学);University of Mannheim(曼海姆大学);INRIA Paris(巴黎国家信息与自动化研究所);Ecole Normale Supérieure(高等师范学校);PSL Research University(巴黎科学实验室大学);Prior Labs(先驱实验室);ELLIS Institute Tübingen(图宾根ELLIS研究所)
Beyond IID: How General Are Tabular Foundation Models, Really?
Prior Labs;University of Freiburg(弗赖堡大学);University of Mannheim(曼海姆大学);INRIA Saclay(法国国家信息与自动化研究所萨克雷研究中心);Technion(技术学院);ELLIS Institute Tübingen(图宾根ELLIS研究所);Zuse School ELIZA(Zuse学校ELIZA)
4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs
Amazon Web Services(亚马逊网络服务);Shanghai Jiaotong University(上海交通大学);The Hong Kong University of Science and Technology(香港科技大学);Fudan University(复旦大学);Tsinghua University(清华大学);Southern University of Science and Technology(南方科技大学);Peking University(北京大学);The Hong Kong Polytechnic University(香港理工大学);Carnegie Mellon University(卡内基梅隆大学)
RCC-GAN: Regularized Compound Conditional GAN for Large-Scale Tabular Data Synthesis
École de Technologie Supérieure (ÉTS), Université du Québec(魁北克大学高等技术学院);Fédération des Caisses Desjardins du Québec(魁北克德信联合会);University of Windsor(温莎大学)
Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment
Flower Labs;University of Cambridge(剑桥大学);University of Auckland(奥克兰大学);University of Melbourne(墨尔本大学);Vector Institute;Fraunhofer IMS(弗劳恩霍夫应用固体物理与材料力学研究所);NetCompany;Gachon University(嘉泉大学);Owkin;Sony AI(索尼人工智能)
Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms
Computer Science Division, Aeronautics Institute of Technology(航空技术研究所计算机科学系);Technology Institute, Federal University of São Paulo(圣保罗联邦大学技术学院);University of Coimbra, CISUC/LASI – Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering(科英布拉大学)
A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking
AI4Health Division, Carl von Ossietzky Universität Oldenburg(AI4Health部门,奥尔登堡大学);CAPASITS, Secretariat of Health of the State of Colima(CAPASITS,科利马州卫生秘书处);Department of Interventional Cardiology, Hospital Puerta de Hierro Colima(介入心脏病学部,科利马医院);Institute for Medical Informatics and Statistics, Kiel University and University Hospital Schleswig-Holstein(医学信息学与统计研究所,基尔大学和石勒苏益格-荷尔斯泰因大学医院);Department of Anesthesiology, Intensive Care Medicine, Emergency Medicine, and Pain Therapy, Carl von Ossietzky Universität & Klinikum Oldenburg(麻醉学、重症医学、急诊医学和疼痛治疗部,奥尔登堡大学及奥尔登堡诊所);Department of Cardiology, Angiology and Intensive Care Medicine, Charité Campus Mitte, German Heart Center of the Charité-University Medicine Berlin(心内科、血管科和重症医学部,Charité梅尔特校区,Charité-大学医学中心柏林德国心脏中心)