大模型对齐与安全 - arXivDaily 专题

2008.04094 2020-09-04 cs.CV cs.LG 57%

Adversarial Examples on Object Recognition: A Comprehensive Survey

Alex Serban, Erik Poll, Joost Visser

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Published in ACM CSUR. arXiv admin note: text overlap with arXiv:1810.01185

2008.12451 2020-08-31 cs.LG cs.RO 57%

Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles

Fei Ye, Pin Wang, Ching-Yao Chan, Jiucai Zhang

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 8 pages, 6 figures

2003.03900 2020-08-25 cs.LG cs.MA cs.RO stat.ML 57%

FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis

Aman Sinha, Matthew O'Kelly, Hongrui Zheng, Rahul Mangharam, John Duchi, Russ Tedrake

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments ICML 2020: https://icml.cc/virtual/2020/poster/6277

2008.02567 2020-08-07 eess.SP cs.CY 57%

An Intelligent Non-Invasive Real Time Human Activity Recognition System for Next-Generation Healthcare

William Taylor, Syed Aziz Shah, Kia Dashtipour, Adnan Zahid, Qammer H. Abbasi, Muhammad Ali Imran

专题命中安全评测：safety(abstract)；分类 cs.CY

Comments 20 pages 18 figures, journal

Journal ref Sensors 2020, 20(9), 2653

2008.00343 2020-08-04 cs.CL 57%

Extracting actionable information from microtexts

Ali Hürriyetoğlu

专题命中安全评测：safety(abstract)；分类 cs.CL

Comments Radboud Univeversity, Dissertation, 2019. Go to https://hdl.handle.net/2066/204517 for the original version

2007.10596 2020-07-22 cs.LG cs.GT stat.ML 57%

Incentives for Federated Learning: a Hypothesis Elicitation Approach

Yang Liu, Jiaheng Wei

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

2005.07310 2020-07-21 cs.CV cs.CL 57%

Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models

Jize Cao, Zhe Gan, Yu Cheng, Licheng Yu, Yen-Chun Chen, Jingjing Liu

专题命中安全评测：alignment(abstract)；分类 cs.CL

Comments Accepted by ECCV 2020 as Spotlight

2007.03215 2020-07-08 cs.CY 57%

RCModel, a Risk Chain Model for Risk Reduction in AI Services

Takashi Matsumoto, Arisa Ema

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

2002.10234 2020-07-06 cs.LG stat.ML 57%

FR-Train: A Mutual Information-Based Approach to Fair and Robust Training

Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh

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

2006.09504 2020-06-22 cs.CV cs.LG 57%

A generalizable saliency map-based interpretation of model outcome

Shailja Thakur, Sebastian Fischmeister

专题命中安全评测：safety(abstract)；分类 cs.LG

2006.09529 2020-06-18 cs.SE cs.AI 57%

Quality Management of Machine Learning Systems

P. Santhanam

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

Comments AAAI-20 Workshop on Engineering Dependable and Secure Machine Learning Systems- February 7, 2020

2005.01196 2020-06-09 cs.CL 57%

On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West, Steffen Eger

专题命中安全评测：alignment(abstract)；分类 cs.CL

Comments ACL2020 Camera Ready (v3: several small fixes, e.g., Unicode errors)

1909.04225 2020-05-26 cs.CL 57%

Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation

Hanjie Chen, Yangfeng Ji

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

Comments 11 pages, NeurIPS 2019 Workshop on Robust AI in Financial Services

2005.09199 2020-05-20 cs.CR cs.CY cs.MM 57%

FrameProv: Towards End-To-End Video Provenance

Mansoor Ahmed-Rengers

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

Journal ref New Security Paradigms Workshop, 2019

2005.02777 2020-05-07 cs.OH cs.AI 57%

AI in society and culture: decision making and values

Katalin Feher, Asta Zelenkauskaite

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

Comments 5 pages, 2 figures

2004.11995 2020-04-28 cs.LG cs.CV eess.IV 57%

Explicit Domain Adaptation with Loosely Coupled Samples

Oliver Scheel, Loren Schwarz, Nassir Navab, Federico Tombari

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Submitted to IROS 2020

2004.11514 2020-04-27 cs.CV cs.CR cs.LG cs.NE 57%

Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers

Loc Truong, Chace Jones, Brian Hutchinson, Andrew August, Brenda Praggastis, Robert Jasper, Nicole Nichols, Aaron Tuor

专题命中安全评测：safety(abstract)；分类 cs.LG

2001.05014 2020-04-21 cs.LG stat.ML 57%

Assurance Monitoring of Cyber-Physical Systems with Machine Learning Components

Dimitrios Boursinos, Xenofon Koutsoukos

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

Comments Accepted at TMCE 2020

2003.01719 2020-03-05 cs.CV cs.LG eess.IV 57%

Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition

Jens Bayer, David Münch, Michael Arens

专题命中安全评测：safety(abstract)；分类 cs.LG

2002.09945 2020-02-25 cs.LG eess.SP 57%

On the Estimation of Complex Circuits Functional Failure Rate by Machine Learning Techniques

Thomas Lange, Aneesh Balakrishnan, Maximilien Glorieux, Dan Alexandrescu, Luca Sterpone

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments arXiv admin note: text overlap with arXiv:2002.08882

2002.01810 2020-02-06 cs.LG cs.CR stat.ML 57%

Understanding the Decision Boundary of Deep Neural Networks: An Empirical Study

David Mickisch, Felix Assion, Florens Greßner, Wiebke Günther, Mariele Motta

专题命中安全评测：safety(abstract)；分类 cs.LG

2001.07838 2020-01-29 cs.SI cs.AI cs.IR 57%

An Approach for Time-aware Domain-based Social Influence Prediction

Bilal Abu-Salih, Kit Yan Chan, Omar Al-Kadi, Marwan Al-Tawil, Pornpit Wongthongtham, Tomayess Issa, Heba Saadeh, Malak Al-Hassan, Bushra Bremie, Abdulaziz Albahlal

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

1912.07394 2019-12-17 eess.SP cs.CV cs.LG 57%

Efficient Error-Tolerant Quantized Neural Network Accelerators

Giulio Gambardella, Johannes Kappauf, Michaela Blott, Christoph Doehring, Martin Kumm, Peter Zipf, Kees Vissers

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 6 pages, 5 figures

Journal ref 2019 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)

1912.02675 2019-12-06 cs.CY 57%

In AI We Trust? Factors That Influence Trustworthiness of AI-infused Decision-Making Processes

Maryam Ashoori, Justin D. Weisz

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

Comments 10 pages

1712.10107 2019-12-03 cs.LG eess.SP stat.ML 57%

Objective evaluation metrics for automatic classification of EEG events

Saeedeh Ziyabari, Vinit Shah, Meysam Golmohammadi, Iyad Obeid, Joseph Picone

专题命中安全评测：alignment(abstract)；分类 cs.LG

Comments 22 pages, 11 figures, 9 tables

1911.02744 2019-11-26 cs.CV cs.LG 57%

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation

Can Qin, Haoxuan You, Lichen Wang, C. -C. Jay Kuo, Yun Fu

专题命中安全评测：alignment(abstract)；分类 cs.LG

Comments 12 pages, 4 figures, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019)

1904.10990 2019-11-26 cs.LG cs.CR cs.SD eess.AS stat.ML 57%

A Robust Approach for Securing Audio Classification Against Adversarial Attacks

Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Paper Accepted for Publication in IEEE Transactions on Information Forensics and Security

1807.01069 2019-11-18 cs.LG stat.ML 57%

Adversarial Robustness Toolbox v1.0.0

Maria-Irina Nicolae, Mathieu Sinn, Minh Ngoc Tran, Beat Buesser, Ambrish Rawat, Martin Wistuba, Valentina Zantedeschi, Nathalie Baracaldo, Bryant Chen, Heiko Ludwig, Ian M. Molloy, Ben Edwards

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

Comments 34 pages

1910.09137 2019-10-22 cs.HC cs.AI 57%

Two Case Studies of Experience Prototyping Machine Learning Systems in the Wild

Qian Yang

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

Comments This is an accepted position paper for the ACM CHI'19 Workshop <Emerging Perspectives in Human-Centered Machine Learning>

1910.03732 2019-10-10 cs.LG cs.RO stat.ML 57%

Ctrl-Z: Recovering from Instability in Reinforcement Learning

Vibhavari Dasagi, Jake Bruce, Thierry Peynot, Jürgen Leitner

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Submitted to ICRA2020, under review

1. 安全评测 9434 篇

Adversarial Examples on Object Recognition: A Comprehensive Survey

Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles

FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis

An Intelligent Non-Invasive Real Time Human Activity Recognition System for Next-Generation Healthcare

Extracting actionable information from microtexts

Incentives for Federated Learning: a Hypothesis Elicitation Approach

Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models

RCModel, a Risk Chain Model for Risk Reduction in AI Services

FR-Train: A Mutual Information-Based Approach to Fair and Robust Training

A generalizable saliency map-based interpretation of model outcome

Quality Management of Machine Learning Systems

On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation

FrameProv: Towards End-To-End Video Provenance

AI in society and culture: decision making and values

Explicit Domain Adaptation with Loosely Coupled Samples

Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers

Assurance Monitoring of Cyber-Physical Systems with Machine Learning Components

Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition

On the Estimation of Complex Circuits Functional Failure Rate by Machine Learning Techniques

Understanding the Decision Boundary of Deep Neural Networks: An Empirical Study

An Approach for Time-aware Domain-based Social Influence Prediction

Efficient Error-Tolerant Quantized Neural Network Accelerators

In AI We Trust? Factors That Influence Trustworthiness of AI-infused Decision-Making Processes

Objective evaluation metrics for automatic classification of EEG events

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation

A Robust Approach for Securing Audio Classification Against Adversarial Attacks

Adversarial Robustness Toolbox v1.0.0

Two Case Studies of Experience Prototyping Machine Learning Systems in the Wild

Ctrl-Z: Recovering from Instability in Reinforcement Learning