大模型对齐与安全 - arXivDaily 专题

2204.13828 2022-05-02 cs.HC cs.AI 57%

Designing for Responsible Trust in AI Systems: A Communication Perspective

Q. Vera Liao, S. Shyam Sundar

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

Comments FAccT 2022 paper draft

2204.00447 2022-04-04 cs.CL 57%

Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation

Francesco Moramarco, Alex Papadopoulos Korfiatis, Mark Perera, Damir Juric, Jack Flann, Ehud Reiter, Anya Belz, Aleksandar Savkov

专题命中安全评测：safety(abstract)；分类 cs.CL

Comments To be published in proceedings of ACL 2022

2204.00103 2022-04-04 stat.ML cs.LG 57%

Scalable Whitebox Attacks on Tree-based Models

Giuseppe Castiglione, Gavin Ding, Masoud Hashemi, Christopher Srinivasa, Ga Wu

专题命中安全评测：safety(abstract)；分类 cs.LG

2203.14265 2022-03-29 cs.LG 57%

A Unified Study of Machine Learning Explanation Evaluation Metrics

Yipei Wang, Xiaoqian Wang

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

2203.12687 2022-03-25 cs.AI cs.HC 57%

Trust in AI and Its Role in the Acceptance of AI Technologies

Hyesun Choung, Prabu David, Arun Ross

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

2203.12620 2022-03-25 eess.IV cs.CV cs.LG 57%

Evaluation of Non-Invasive Thermal Imaging for detection of Viability of Onchocerciasis worms

Ronak Dedhiya, Siva Teja Kakileti, Goutham Deepu, Kanchana Gopinath, Nicholas Opoku, Christopher King, Geetha Manjunath

专题命中安全评测：alignment(abstract)；分类 cs.LG

Comments It is submitted to EMBC 2022 and is currently under review

2203.10534 2022-03-22 cs.CR cs.CY cs.SY eess.SY 57%

Synergy between 6G and AI: Open Future Horizons and Impending Security Risks

Elias Yaacoub

专题命中安全评测：safety(abstract)；分类 cs.CY

2203.09982 2022-03-21 cs.CL 57%

CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding

Milan Gritta, Ruoyu Hu, Ignacio Iacobacci

专题命中安全评测：alignment(abstract)；分类 cs.CL

Comments Long paper (multilingual track) to appear at ACL (Findings) 2022

2203.09293 2022-03-18 cs.CV cs.LG cs.MA 57%

PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer

Lina Achaji, Thierno Barry, Thibault Fouqueray, Julien Moreau, Francois Aioun, Francois Charpillet

专题命中安全评测：safety(abstract)；分类 cs.LG

2203.05488 2022-03-15 cs.LG math.GT q-bio.NC 57%

Geometric and Topological Inference for Deep Representations of Complex Networks

Baihan Lin

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

Comments To appear in Proceeding of WWW 2022. This work extends our prior work (arXiv:1810.02923, arXiv:1906.09264, arXiv:1902.10658) and put them in perspectives along with many other ongoing research in this direction

2111.10484 2022-03-14 cs.AI cs.SY eess.SY 57%

Inter-Domain Fusion for Enhanced Intrusion Detection in Power Systems: An Evidence Theoretic and Meta-Heuristic Approach

Abhijeet Sahu, Katherine Davis

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

Comments 11 pages, 21 Figures (out of which 17 sub-figures), 1 table

Journal ref MDPI Sensors 2022

2203.05323 2022-03-11 cs.LG 57%

Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness

Yiqi Zhong, Lei Wu, Xianming Liu, Junjun Jiang

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

Comments Accepted by the AAAI2022 Workshop on Adversarial Machine Learning and Beyond as a competition paper

2203.01864 2022-03-04 cs.LG cs.CV 57%

Robustness and Adaptation to Hidden Factors of Variation

William Paul, Philippe Burlina

专题命中安全评测：alignment(abstract)；分类 cs.LG

2203.00469 2022-03-02 cs.CV cs.AI cs.MM 57%

Compliance Challenges in Forensic Image Analysis Under the Artificial Intelligence Act

Benedikt Lorch, Nicole Scheler, Christian Riess

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

2202.02094 2022-03-01 eess.SY cs.LG cs.SY 57%

Numerical Demonstration of Multiple Actuator Constraint Enforcement Algorithm for a Molten Salt Loop

Akshay J. Dave, Haoyu Wang, Roberto Ponciroli, Richard B. Vilim

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 4 pages, 6 figures. Submitted to 2022 American Nuclear Society Annual Meeting

2202.08934 2022-02-21 cs.LG 57%

Handling Imbalanced Datasets Through Optimum-Path Forest

Leandro Aparecido Passos, Danilo S. Jodas, Luiz C. F. Ribeiro, Marco Akio, Andre Nunes de Souza, João Paulo Papa

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

2202.08393 2022-02-18 cs.LG cs.RO 57%

Robust Reinforcement Learning via Genetic Curriculum

Yeeho Song, Jeff Schneider

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Accepted to 2022 IEEE International Conference on Robotics and Automation (ICRA)

2202.07183 2022-02-16 cs.CR cs.AI cs.CV 57%

A Survey of Neural Trojan Attacks and Defenses in Deep Learning

Jie Wang, Ghulam Mubashar Hassan, Naveed Akhtar

专题命中安全评测：safety(abstract)；分类 cs.AI

Comments 15 pages

2202.01783 2022-02-07 eess.IV cs.CV cs.LG 57%

Oral cancer detection and interpretation: Deep multiple instance learning versus conventional deep single instance learning

Nadezhda Koriakina, Nataša Sladoje, Vladimir Bašić, Joakim Lindblad

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

2202.01319 2022-02-04 cs.LG 57%

Deep Learning for Epidemiologists: An Introduction to Neural Networks

Stylianos Serghiou, Kathryn Rough

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 35 pages with 1.5 spacing, 6 figures

2202.00001 2022-02-02 q-bio.QM cs.LG 57%

Insights into performance evaluation of com-pound-protein interaction prediction methods

Adiba Yaseen, Imran Amin, Naeem Akhter, Asa Ben-Hur, Fayyaz Minhas

专题命中安全评测：alignment(abstract)；分类 cs.LG

Comments Supplementary information: Supplementary data files are available as part of the GitHub repository

2106.08961 2022-01-25 cs.LG cs.SY eess.SY 57%

A Direct Slip Ratio Estimation Method based on an Intelligent Tire and Machine Learning

Nan Xu, Zepeng Tang, Hassan Askari, Jianfeng Zhou, Amir Khajepour

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 12 pages, 25 figures, 2 tables

2201.04777 2022-01-14 cs.CV cs.LG 57%

A Survey on Masked Facial Detection Methods and Datasets for Fighting Against COVID-19

Bingshu Wang, Jiangbin Zheng, C. L. Philip Chen

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 21 pages, 9 figures, 5 tables. IEEE Transactions on Artificial Intelligence, 2021, early access

2112.03615 2021-12-14 cs.CV cs.AI 57%

Saliency Diversified Deep Ensemble for Robustness to Adversaries

Alex Bogun, Dimche Kostadinov, Damian Borth

专题命中安全评测：alignment(abstract)；分类 cs.AI

Comments Accepted to AAAI Workshop on Adversarial Machine Learning and Beyond 2022

2111.15518 2021-12-10 cs.LG 57%

Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Images

Dvij Kalaria, Aritra Hazra, Partha Pratim Chakrabarti

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Accepted at Adversarial Machine Learning (AdvML) workshop, AAAI 2022

2106.06317 2021-12-07 cs.LG 57%

Automatic Risk Adaptation in Distributional Reinforcement Learning

Frederik Schubert, Theresa Eimer, Bodo Rosenhahn, Marius Lindauer

专题命中安全评测：safety(abstract)；分类 cs.LG

Journal ref Reinforcement Learning for Real Life Workshop, ICML 2021

2112.00115 2021-12-02 cs.RO cs.AI 57%

Risk-based implementation of COLREGs for autonomous surface vehicles using deep reinforcement learning

Thomas Nakken Larsen, Amalie Heiberg, Eivind Meyer, Adil Rasheeda, Omer San, Damiano Varagnolo

专题命中安全评测：safety(abstract)；分类 cs.AI

2111.14142 2021-11-30 cs.SE cs.AI 57%

Agility in Software 2.0 -- Notebook Interfaces and MLOps with Buttresses and Rebars

Markus Borg

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

Comments Preprint of paper accompanying keynote address at the 6th International Conference on Lean and Agile Software Development (Jan 22, 2022)

2111.09930 2021-11-22 cs.LG 57%

Learning To Estimate Regions Of Attraction Of Autonomous Dynamical Systems Using Physics-Informed Neural Networks

Cody Scharzenberger, Joe Hays

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 31 pages, 17 figures

2111.07568 2021-11-16 cs.AI 57%

Can Graph Neural Networks Learn to Solve MaxSAT Problem?

Minghao Liu, Fuqi Jia, Pei Huang, Fan Zhang, Yuchen Sun, Shaowei Cai, Feifei Ma, Jian Zhang

专题命中安全评测：alignment(abstract)；分类 cs.AI

1. 安全评测 9434 篇

Designing for Responsible Trust in AI Systems: A Communication Perspective

Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation

Scalable Whitebox Attacks on Tree-based Models

A Unified Study of Machine Learning Explanation Evaluation Metrics

Trust in AI and Its Role in the Acceptance of AI Technologies

Evaluation of Non-Invasive Thermal Imaging for detection of Viability of Onchocerciasis worms

Synergy between 6G and AI: Open Future Horizons and Impending Security Risks

CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding

PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer

Geometric and Topological Inference for Deep Representations of Complex Networks

Inter-Domain Fusion for Enhanced Intrusion Detection in Power Systems: An Evidence Theoretic and Meta-Heuristic Approach

Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness

Robustness and Adaptation to Hidden Factors of Variation

Compliance Challenges in Forensic Image Analysis Under the Artificial Intelligence Act

Numerical Demonstration of Multiple Actuator Constraint Enforcement Algorithm for a Molten Salt Loop

Handling Imbalanced Datasets Through Optimum-Path Forest

Robust Reinforcement Learning via Genetic Curriculum

A Survey of Neural Trojan Attacks and Defenses in Deep Learning

Oral cancer detection and interpretation: Deep multiple instance learning versus conventional deep single instance learning

Deep Learning for Epidemiologists: An Introduction to Neural Networks

Insights into performance evaluation of com-pound-protein interaction prediction methods

A Direct Slip Ratio Estimation Method based on an Intelligent Tire and Machine Learning

A Survey on Masked Facial Detection Methods and Datasets for Fighting Against COVID-19

Saliency Diversified Deep Ensemble for Robustness to Adversaries

Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Images

Automatic Risk Adaptation in Distributional Reinforcement Learning

Risk-based implementation of COLREGs for autonomous surface vehicles using deep reinforcement learning

Agility in Software 2.0 -- Notebook Interfaces and MLOps with Buttresses and Rebars

Learning To Estimate Regions Of Attraction Of Autonomous Dynamical Systems Using Physics-Informed Neural Networks

Can Graph Neural Networks Learn to Solve MaxSAT Problem?