大模型对齐与安全 - arXivDaily 专题

2105.02595 2021-05-07 cs.LG 57%

Scaling up Memory-Efficient Formal Verification Tools for Tree Ensembles

John Törnblom, Simin Nadjm-Tehrani

专题命中安全评测：safety(abstract)；分类 cs.LG

2105.02540 2021-05-07 cs.SE cs.AI 57%

Distribution Awareness for AI System Testing

David Berend

专题命中安全评测：safety(abstract)；分类 cs.AI

Comments 2 pages, 1 figure, pre-print

2101.10305 2021-04-22 cs.MA cs.AI 57%

Accumulating Risk Capital Through Investing in Cooperation

Charlotte Roman, Michael Dennis, Andrew Critch, Stuart Russell

专题命中安全评测：safety(abstract)；分类 cs.AI

2104.06561 2021-04-15 cs.CY 57%

Impact of risk factors on work zone crashes using logistic models and Random Forest

Huthaifa I Ashqar, Qadri H Shaheen, Suleiman A Ashur, Hesham A Rakha

专题命中安全评测：safety(abstract)；分类 cs.CY

2104.05824 2021-04-14 cs.CL 57%

Evaluating Saliency Methods for Neural Language Models

Shuoyang Ding, Philipp Koehn

专题命中安全评测：trustworthy(abstract)；分类 cs.CL

Comments 19 pages, 2 figures, Accepted for NAACL 2021

2104.01742 2021-04-06 cs.LG cs.CV 57%

Explainability-aided Domain Generalization for Image Classification

Robin M. Schmidt

专题命中安全评测：alignment(abstract)；分类 cs.LG

2103.15580 2021-03-30 cs.LG 57%

Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks

Jens Henriksson, Christian Berger, Markus Borg, Lars Tornberg, Sankar Raman Sathyamoorthy, Cristofer Englund

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 8 pages, 7 figures, presented at SEAA 2019

2103.13815 2021-03-26 cs.LG 57%

Fast Approximate Spectral Normalization for Robust Deep Neural Networks

Zhixin Pan, Prabhat Mishra

专题命中安全评测：safety(abstract)；分类 cs.LG

2010.15100 2021-03-16 cs.LG stat.ML 57%

Evaluating Model Robustness and Stability to Dataset Shift

Adarsh Subbaswamy, Roy Adams, Suchi Saria

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

1911.03010 2021-03-10 cs.LG cs.NE 57%

Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study

Mohammad Mahdi Bejani, Mehdi Ghatee

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments A review paper with 8 pages, 2 figures, and 2 tables, submitted to 18th International Conference on Traffic & Transportation Engineering, Tehran, February 25-27, 2020. Artificial Intelligence Review (2021)

2003.06404 2021-03-03 cs.AI cs.RO 57%

A Survey of End-to-End Driving: Architectures and Training Methods

Ardi Tampuu, Maksym Semikin, Naveed Muhammad, Dmytro Fishman, Tambet Matiisen

专题命中安全评测：safety(abstract)；分类 cs.AI

Journal ref IEEE Transactions on Neural Networks and Learning Systems, 2020

2102.05856 2021-02-12 cs.LG 57%

Predicting Clinical Deterioration in Hospitals

Laleh Jalali, Hsiu-Khuern Tang, Richard H. Goldstein, Joaqun Alvarez Rodrguez

专题命中安全评测：safety(abstract)；分类 cs.LG

2102.04221 2021-02-09 cs.CY 57%

The Sanction of Authority: Promoting Public Trust in AI

Bran Knowles, John T. Richards

专题命中安全评测：trustworthy(abstract)；分类 cs.CY

2102.00509 2021-02-02 cs.SI cs.CL 57%

TruthBot: An Automated Conversational Tool for Intent Learning, Curated Information Presenting, and Fake News Alerting

Ankur Gupta, Yash Varun, Prarthana Das, Nithya Muttineni, Parth Srivastava, Hamim Zafar, Tanmoy Chakraborty, Swaprava Nath

专题命中安全评测：trustworthy(abstract)；分类 cs.CL

Comments 17 pages, 11 images

1910.05112 2021-01-20 cs.LG 57%

Organization of machine learning based product development as per ISO 26262 and ISO/PAS 21448

Krystian Radlak, Michał Szczepankiewicz, Tim Jones, Piotr Serwa

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 10 pages, 2 figures

2101.02689 2021-01-08 stat.ML cs.LG 57%

The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networks

Arno Blaas, Stephen J. Roberts

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 4 pages, 2 tables, AAAI 2021 Workshop Towards Robust, Secure and Efficient Machine Learning

2012.08822 2020-12-17 cs.RO cs.LG 57%

A comparative evaluation of machine learning methods for robot navigation through human crowds

Anastasia Gaydashenko, Daniel Kudenko, Aleksei Shpilman

专题命中安全评测：safety(abstract)；分类 cs.LG

2009.05166 2020-12-16 cs.CL 57%

FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding

Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu

专题命中安全评测：alignment(abstract)；分类 cs.CL

Comments Accepted to AAAI 2021; Top-1 Performance on XTREME (https://sites.research.google/xtreme, September 8, 2020) and XGLUE (https://microsoft.github.io/XGLUE, September 14, 2020) benchmark

2012.07278 2020-12-15 stat.ML cs.LG stat.AP 57%

Learning how to approve updates to machine learning algorithms in non-stationary settings

Jean Feng

专题命中安全评测：safety(abstract)；分类 cs.LG

2012.02118 2020-12-04 cs.RO cs.LG 57%

Fast-reactive probabilistic motion planning for high-dimensional robots

Siyu Dai, Andreas Hofmann, Brian C. Williams

专题命中安全评测：safety(abstract)；分类 cs.LG

2011.08008 2020-11-30 cs.CV cs.AI 57%

Towards Map-Based Validation of Semantic Segmentation Masks

Laura von Rueden, Tim Wirtz, Fabian Hueger, Jan David Schneider, Christian Bauckhage

专题命中安全评测：safety(abstract)；分类 cs.AI

2011.11631 2020-11-25 cs.LG 57%

Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals

Tsung-Yu Hsieh, Suhang Wang, Yiwei Sun, Vasant Honavar

专题命中安全评测：trustworthy(abstract)；分类 cs.LG

2010.05496 2020-11-04 cs.CL stat.ML 57%

Feature Extraction of Text for Deep Learning Algorithms: Application on Fake News Detection

HyeonJun Kim

专题命中安全评测：trustworthy(abstract)；分类 cs.CL

Comments 8 pages

2010.15551 2020-10-30 stat.ML cs.LG 57%

Investigating the Robustness of Artificial Intelligent Algorithms with Mixture Experiments

Jiayi Lian, Laura Freeman, Yili Hong, Xinwei Deng

专题命中安全评测：safety(abstract)；分类 cs.LG

2010.08140 2020-10-19 cs.AI 57%

Monitoring Trust in Human-Machine Interactions for Public Sector Applications

Farhana Faruqe, Ryan Watkins, Larry Medsker

专题命中安全评测：trustworthy(abstract)；分类 cs.AI

Comments Presented at AAAI FSS-20: Artificial Intelligence in Government and Public Sector, Washington, DC, USA

2010.07765 2020-10-16 cs.LG stat.ML 57%

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

Luka Rimanic, Cedric Renggli, Bo Li, Ce Zhang

专题命中安全评测：safety(abstract)；分类 cs.LG

2010.04890 2020-10-13 cs.LG math.ST stat.ML stat.TH 57%

Rare-Event Simulation for Neural Network and Random Forest Predictors

Yuanlu Bai, Zhiyuan Huang, Henry Lam, Ding Zhao

专题命中安全评测：safety(abstract)；分类 cs.LG

2010.04260 2020-10-12 cs.CL cs.IR 57%

Fake Reviews Detection through Analysis of Linguistic Features

Faranak Abri, Luis Felipe Gutierrez, Akbar Siami Namin, Keith S. Jones, David R. W. Sears

专题命中安全评测：trustworthy(abstract)；分类 cs.CL

Comments The pre-print of a paper to appear in the proceedings of the IEEE International Conference on Machine Learning Applications (ICMLA 2020), 11 pages, 3 figures, 5 tables

2009.09358 2020-09-22 cs.LG stat.ML 57%

Out-Of-Bag Anomaly Detection

Egor Klevak, Sangdi Lin, Andy Martin, Ondrej Linda, Eric Ringger

专题命中安全评测：trustworthy(abstract)；分类 cs.LG

Comments 13 pages, 4 figures, KDD 2020 TrueFact Workshop: Making a Credible Web for Tomorrow

2009.06349 2020-09-15 cs.LG cs.HC 57%

Play MNIST For Me! User Studies on the Effects of Post-Hoc, Example-Based Explanations & Error Rates on Debugging a Deep Learning, Black-Box Classifier

Courtney Ford, Eoin M. Kenny, Mark T. Keane

专题命中安全评测：trustworthy(abstract)；分类 cs.LG

Comments 2 Figures, 1 Table, 8 pages

Journal ref IJCAI-20 Workshop on Explainable AI (XAI), September 2020

1. 安全评测 9434 篇

Scaling up Memory-Efficient Formal Verification Tools for Tree Ensembles

Distribution Awareness for AI System Testing

Accumulating Risk Capital Through Investing in Cooperation

Impact of risk factors on work zone crashes using logistic models and Random Forest

Evaluating Saliency Methods for Neural Language Models

Explainability-aided Domain Generalization for Image Classification

Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks

Fast Approximate Spectral Normalization for Robust Deep Neural Networks

Evaluating Model Robustness and Stability to Dataset Shift

Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study

A Survey of End-to-End Driving: Architectures and Training Methods

Predicting Clinical Deterioration in Hospitals

The Sanction of Authority: Promoting Public Trust in AI

TruthBot: An Automated Conversational Tool for Intent Learning, Curated Information Presenting, and Fake News Alerting

Organization of machine learning based product development as per ISO 26262 and ISO/PAS 21448

The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networks

A comparative evaluation of machine learning methods for robot navigation through human crowds

FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding

Learning how to approve updates to machine learning algorithms in non-stationary settings

Fast-reactive probabilistic motion planning for high-dimensional robots

Towards Map-Based Validation of Semantic Segmentation Masks

Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals

Feature Extraction of Text for Deep Learning Algorithms: Application on Fake News Detection

Investigating the Robustness of Artificial Intelligent Algorithms with Mixture Experiments

Monitoring Trust in Human-Machine Interactions for Public Sector Applications

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

Rare-Event Simulation for Neural Network and Random Forest Predictors

Fake Reviews Detection through Analysis of Linguistic Features

Out-Of-Bag Anomaly Detection

Play MNIST For Me! User Studies on the Effects of Post-Hoc, Example-Based Explanations & Error Rates on Debugging a Deep Learning, Black-Box Classifier