大模型对齐与安全 - arXivDaily 专题

2209.06529 2022-09-15 cs.LG cs.CR 79%

Data Privacy and Trustworthy Machine Learning

Martin Strobel, Reza Shokri

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

Journal ref Published in: IEEE Security & Privacy ( Volume: 20, Issue: 5, Sept.-Oct. 2022)

2207.12615 2022-07-27 cs.LG 79%

Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety

Puja Trivedi, Danai Koutra, Jayaraman J. Thiagarajan

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

Comments Principles of Distribution Shift (PODS) Workshop at ICML 2022, 4 pages, 2 figures

2207.10809 2022-07-25 cs.CR cs.AI 79%

Security and Safety Aspects of AI in Industry Applications

Hans Dermot Doran

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

Comments As presented at the Embedded World Conference, Nuremberg, 2022

2207.09312 2022-07-20 eess.IV cs.CV cs.LG 79%

Towards Trustworthy Healthcare AI: Attention-Based Feature Learning for COVID-19 Screening With Chest Radiography

Kai Ma, Pengcheng Xi, Karim Habashy, Ashkan Ebadi, Stéphane Tremblay, Alexander Wong

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

Comments Accepted to 39th International Conference on Machine Learning, Workshop on Healthcare AI and COVID-19

2203.07505 2022-07-15 eess.SY cs.LG cs.SY 79%

Closing the Loop: A Framework for Trustworthy Machine Learning in Power Systems

Jochen Stiasny, Samuel Chevalier, Rahul Nellikkath, Brynjar Sævarsson, Spyros Chatzivasileiadis

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

Comments In proceedings of the 11th Bulk Power Systems Dynamics and Control Symposium (IREP 2022), July 25-30, 2022, Banff, Canada. 21 pages, 12 figures, 5 tables

2206.09523 2022-06-22 eess.AS cs.CY cs.SD 79%

Towards Trustworthy Edge Intelligence: Insights from Voice-Activated Services

W. T. Hutiri, A. Y. Ding

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

2206.03044 2022-06-22 cs.AI cs.LO cs.NE cs.SE 79%

CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness

Julien Girard-Satabin, Michele Alberti, François Bobot, Zakaria Chihani, Augustin Lemesle

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

Journal ref AISafety, Jul 2022, Vienne, Austria

2206.07506 2022-06-16 cs.HC cs.CY 79%

Legal Provocations for HCI in the Design and Development of Trustworthy Autonomous Systems

Lachlan D. Urquhart, Glenn McGarry, Andy Crabtree

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

2206.01909 2022-06-07 cs.LG 79%

Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation

Haohan Wang, Zeyi Huang, Xindi Wu, Eric P. Xing

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

Comments to appear at KDD 2022, the software package is at https://github.com/jyanln/AlignReg. arXiv admin note: text overlap with arXiv:2011.13052

2204.14095 2022-05-31 cs.CV cs.AI 79%

PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining

Yuting Gao, Jinfeng Liu, Zihan Xu, Jun Zhang, Ke Li, Rongrong Ji, Chunhua Shen

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

2103.15059 2022-05-09 cs.AI 79%

A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning

Rui Zhang, Bayu Distiawan Trisedy, Miao Li, Yong Jiang, Jianzhong Qi

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

Comments to appear in VLDB Journal, 2022

2107.09234 2022-03-28 cs.LG 79%

Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior

Angie Boggust, Benjamin Hoover, Arvind Satyanarayan, Hendrik Strobelt

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

Comments 17 pages, 10 figures. Published in CHI 2022. For more details, see http://shared-interest.csail.mit.edu

2202.12653 2022-02-28 cs.LG stat.ML 79%

Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection

Bang Xiang Yong, Alexandra Brintrup

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

2101.03042 2022-02-15 cs.LG cs.CR 79%

Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective

Pulei Xiong, Scott Buffett, Shahrear Iqbal, Philippe Lamontagne, Mohammad Mamun, Heather Molyneaux

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

Comments 20 pages (58 pages pre-print), 6 figures

Journal ref Journal of Information Security and Applications 65 (2022) 103121

2202.05313 2022-02-14 cs.AI cs.SE 79%

Integrating Testing and Operation-related Quantitative Evidences in Assurance Cases to Argue Safety of Data-Driven AI/ML Components

Michael Kläs, Lisa Jöckel, Rasmus Adler, Jan Reich

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

Comments 8 pages

2202.01934 2022-02-07 cs.LG 79%

Smartphone-based Hard-braking Event Detection at Scale for Road Safety Services

Luyang Liu, David Racz, Kara Vaillancourt, Julie Michelman, Matt Barnes, Stefan Mellem, Paul Eastham, Bradley Green, Charles Armstrong, Rishi Bal, Shawn O'Banion, Feng Guo

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

2112.09998 2021-12-21 cs.RO cs.LG cs.SY eess.SY 79%

Learning-based methods to model small body gravity fields for proximity operations: Safety and Robustness

Daniel Neamati, Yashwanth Kumar Nakka, Soon-Jo Chung

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

Comments Accepted Scitech, AI for Space

2112.03024 2021-12-07 cs.CL 79%

Domain-oriented Language Pre-training with Adaptive Hybrid Masking and Optimal Transport Alignment

Denghui Zhang, Zixuan Yuan, Yanchi Liu, Hao Liu, Fuzhen Zhuang, Hui Xiong, Haifeng Chen

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

2110.02707 2021-10-07 cs.SE cs.AI 79%

Trustworthy Artificial Intelligence and Process Mining: Challenges and Opportunities

Andrew Pery, Majid Rafiei, Michael Simon, Wil M. P. van der Aalst

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

2110.01232 2021-10-05 cs.AI 79%

Benchmarking Safety Monitors for Image Classifiers with Machine Learning

Raul Sena Ferreira, Jean Arlat, Jeremie Guiochet, Hélène Waeselynck

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

Journal ref 26th IEEE Pacific Rim International Symposium on Dependable Computing (PRDC 2021), IEEE, Dec 2021, Perth, Australia

2105.10142 2021-09-28 cs.CV cs.LG 79%

Safety Metrics for Semantic Segmentation in Autonomous Driving

Chih-Hong Cheng, Alois Knoll, Hsuan-Cheng Liao

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

Comments Paper accepted at IEEE AI Test'21

1903.01287 2021-09-16 math.OC cs.LG 79%

Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming

Mahyar Fazlyab, Manfred Morari, George J. Pappas

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

2109.01531 2021-09-06 cs.LG 79%

MACEst: The reliable and trustworthy Model Agnostic Confidence Estimator

Rhys Green, Matthew Rowe, Alberto Polleri

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

2108.06080 2021-08-16 cs.LG 79%

TDM: Trustworthy Decision-Making via Interpretability Enhancement

Daoming Lyu, Fangkai Yang, Hugh Kwon, Wen Dong, Levent Yilmaz, Bo Liu

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

Journal ref IEEE Transactions on Emerging Topics in Computational Intelligence 0 (2021) 1-12

2101.08231 2021-08-13 cs.CL 79%

Word Alignment by Fine-tuning Embeddings on Parallel Corpora

Zi-Yi Dou, Graham Neubig

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

Comments EACL 2021

2006.06466 2021-06-08 cs.LG stat.ML 79%

How Interpretable and Trustworthy are GAMs?

Chun-Hao Chang, Sarah Tan, Ben Lengerich, Anna Goldenberg, Rich Caruana

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

Comments Accepted in 2021 KDD

2106.00512 2021-06-02 cs.LG 79%

The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning

Katharina Morik, Helena Kotthaus, Lukas Heppe, Danny Heinrich, Raphael Fischer, Andreas Pauly, Nico Piatkowski

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

2003.05434 2021-04-26 cs.SE cs.AI 79%

Developing and Operating Artificial Intelligence Models in Trustworthy Autonomous Systems

Silverio Martínez-Fernández, Xavier Franch, Andreas Jedlitschka, Marc Oriol, Adam Trendowicz

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

Comments 9 pages, 1 figure, preprint. Accepted in RCIS 2021

1911.13073 2020-07-21 cs.CV cs.LG eess.IV 79%

Attributional Robustness Training using Input-Gradient Spatial Alignment

Mayank Singh, Nupur Kumari, Puneet Mangla, Abhishek Sinha, Vineeth N Balasubramanian, Balaji Krishnamurthy

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

Comments ECCV 2020, Code at https://github.com/nupurkmr9/Attributional-Robustness

2003.01155 2020-07-01 cs.SE cs.LG 79%

Towards Probability-based Safety Verification of Systems with Components from Machine Learning

Hermann Kaindl, Stefan Kramer

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

Comments Second (revised) version for public access

1. 安全评测 9311 篇

Data Privacy and Trustworthy Machine Learning

Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety

Security and Safety Aspects of AI in Industry Applications

Towards Trustworthy Healthcare AI: Attention-Based Feature Learning for COVID-19 Screening With Chest Radiography

Closing the Loop: A Framework for Trustworthy Machine Learning in Power Systems

Towards Trustworthy Edge Intelligence: Insights from Voice-Activated Services

CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness

Legal Provocations for HCI in the Design and Development of Trustworthy Autonomous Systems

Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation

PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining

A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning

Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior

Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection

Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective

Integrating Testing and Operation-related Quantitative Evidences in Assurance Cases to Argue Safety of Data-Driven AI/ML Components

Smartphone-based Hard-braking Event Detection at Scale for Road Safety Services

Learning-based methods to model small body gravity fields for proximity operations: Safety and Robustness

Domain-oriented Language Pre-training with Adaptive Hybrid Masking and Optimal Transport Alignment

Trustworthy Artificial Intelligence and Process Mining: Challenges and Opportunities

Benchmarking Safety Monitors for Image Classifiers with Machine Learning

Safety Metrics for Semantic Segmentation in Autonomous Driving

Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming

MACEst: The reliable and trustworthy Model Agnostic Confidence Estimator

TDM: Trustworthy Decision-Making via Interpretability Enhancement

Word Alignment by Fine-tuning Embeddings on Parallel Corpora

How Interpretable and Trustworthy are GAMs?

The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning

Developing and Operating Artificial Intelligence Models in Trustworthy Autonomous Systems

Attributional Robustness Training using Input-Gradient Spatial Alignment

Towards Probability-based Safety Verification of Systems with Components from Machine Learning