大模型对齐与安全 - arXivDaily 专题

1910.02461 2019-10-08 cs.AI cs.RO 57%

Risk-Aware Reasoning for Autonomous Vehicles

Majid Khonji, Jorge Dias, Lakmal Seneviratne

专题命中安全评测：safety(abstract)；分类 cs.AI

1910.01380 2019-10-04 cs.AI 57%

GRAVITAS: A Model Checking Based Planning and Goal Reasoning Framework for Autonomous Systems

Hadrien Bride, Jin Song Dong, Ryan Green, Zhe Hou, Brendan Mahony, Martin Oxenham

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

1906.11392 2019-09-24 math.OC cs.LG stat.ML 57%

From self-tuning regulators to reinforcement learning and back again

Nikolai Matni, Alexandre Proutiere, Anders Rantzer, Stephen Tu

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Tutorial paper, 2019 IEEE Conference on Decision and Control, to appear

1909.08864 2019-09-20 cs.CR cs.LG stat.ML 57%

Adversarial Vulnerability Bounds for Gaussian Process Classification

Michael Thomas Smith, Kathrin Grosse, Michael Backes, Mauricio A Alvarez

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 10 pages + 2 pages references + 7 pages of supplementary. 12 figures. Submitted to AAAI

1609.05625 2019-09-04 cs.CL 57%

The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition

Ahmed Ali, Peter Bell, James Glass, Yacine Messaoui, Hamdy Mubarak, Steve Renals, Yifan Zhang

专题命中安全评测：alignment(abstract)；分类 cs.CL

1904.00001 2019-08-23 cs.SE cs.LG 57%

Engineering problems in machine learning systems

Hiroshi Kuwajima, Hirotoshi Yasuoka, Toshihiro Nakae

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments 20 pages, 4 figures, 4 tables

1809.00065 2019-07-30 cs.LG cs.CR stat.ML 57%

MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks

Siwakorn Srisakaokul, Yuhao Zhang, Zexuan Zhong, Wei Yang, Tao Xie, Bo Li

专题命中安全评测：safety(abstract)；分类 cs.LG

1907.01627 2019-07-04 cs.DB cs.AI 57%

Rule Applicability on RDF Triplestore Schemas

Paolo Pareti, George Konstantinidis, Timothy J. Norman, Murat Şensoy

专题命中安全评测：safety(abstract)；分类 cs.AI

Comments AI for Internet of Things Workshop, co-located with the 28th International Joint Conference on Artificial Intelligence (IJCAI-19)

1906.07982 2019-06-20 cs.LG cs.CR stat.ML 57%

A unified view on differential privacy and robustness to adversarial examples

Rafael Pinot, Florian Yger, Cédric Gouy-Pailler, Jamal Atif

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

1706.03922 2019-06-20 stat.ML cs.CR cs.LG 57%

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

Yizhen Wang, Somesh Jha, Kamalika Chaudhuri

专题命中安全评测：safety(abstract)；分类 cs.LG

Journal ref International Conference on Machine Learning (ICML) 2018, Page 5133--5142

1905.13358 2019-06-03 cs.CL cs.CV 57%

Multi-modal Discriminative Model for Vision-and-Language Navigation

Haoshuo Huang, Vihan Jain, Harsh Mehta, Jason Baldridge, Eugene Ie

专题命中安全评测：alignment(abstract)；分类 cs.CL

Comments Accepted at SpLU-RoboNLP 2019 (workshop at NAACL)

1905.07679 2019-05-21 cs.LG stat.ML 57%

Predicting Model Failure using Saliency Maps in Autonomous Driving Systems

Sina Mohseni, Akshay Jagadeesh, Zhangyang Wang

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Presented at ICML 2019 Workshop on Uncertainty and Robustness in Deep Learning

1905.04172 2019-05-13 stat.ML cs.CV cs.LG 57%

On the Connection Between Adversarial Robustness and Saliency Map Interpretability

Christian Etmann, Sebastian Lunz, Peter Maass, Carola-Bibiane Schönlieb

专题命中安全评测：alignment(abstract)；分类 cs.LG

Comments 12 pages, accepted for publication at the 36th International Conference on Machine Learning 2019

1903.07994 2019-03-20 cs.CR cs.LG stat.ML 57%

An Evaluation of Bitcoin Address Classification based on Transaction History Summarization

Yu-Jing Lin, Po-Wei Wu, Cheng-Han Hsu, I-Ping Tu, Shih-wei Liao

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

Comments 8 pages; accepted by ICBC 2019

1810.01185 2019-02-19 cs.CV cs.CR cs.LG cs.NE 57%

Adversarial Examples - A Complete Characterisation of the Phenomenon

Alexandru Constantin Serban, Erik Poll, Joost Visser

专题命中安全评测：safety(abstract)；分类 cs.LG

1809.07893 2019-02-07 cs.GT cs.AI 57%

Solving Large Extensive-Form Games with Strategy Constraints

Trevor Davis, Kevin Waugh, Michael Bowling

专题命中安全评测：safety(abstract)；分类 cs.AI

Comments Appeared in AAAI 2019

1812.01647 2018-12-06 cs.LG cs.CR stat.ML 57%

Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures

Jonathan Uesato, Ananya Kumar, Csaba Szepesvari, Tom Erez, Avraham Ruderman, Keith Anderson, Krishmamurthy, Dvijotham, Nicolas Heess, Pushmeet Kohli

专题命中安全评测：safety(abstract)；分类 cs.LG

1809.08352 2018-09-25 stat.ML cs.CV cs.LG 57%

Unrestricted Adversarial Examples

Tom B. Brown, Nicholas Carlini, Chiyuan Zhang, Catherine Olsson, Paul Christiano, Ian Goodfellow

专题命中安全评测：safety(abstract)；分类 cs.LG

1808.00516 2018-08-03 cs.RO cs.LG stat.ML 57%

A Learning-Based Framework for Two-Dimensional Vehicle Maneuver Prediction over V2V Networks

Hossein Nourkhiz Mahjoub, Amin Tahmasbi-Sarvestani, Hadi Kazemi, Yaser P. Fallah

专题命中安全评测：safety(abstract)；分类 cs.LG

Journal ref 2017 IEEE Cyber Science and Technology Congress(CyberSciTech), Orlando, FL, 2017, pp. 156-163

1807.01619 2018-07-06 cs.LG stat.ML 57%

Ensemble learning with Conformal Predictors: Targeting credible predictions of conversion from Mild Cognitive Impairment to Alzheimer's Disease

Telma Pereira, Sandra Cardoso, Dina Silva, Manuela Guerreiro, Alexandre de Mendonça, Sara C. Madeira

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

Comments 4 pages, 1 figure, accepted for presentation at the KDD Workshop on Machine Learning for Medicine and Healthcare, London, UK, August 2018

1805.02754 2018-05-09 cs.AI cs.RO 57%

Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment

Thomio Watanabe, Denis Wolf

专题命中安全评测：safety(abstract)；分类 cs.AI

1712.04248 2018-02-19 stat.ML cs.CR cs.CV cs.LG cs.NE 57%

Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

Wieland Brendel, Jonas Rauber, Matthias Bethge

专题命中安全评测：safety(abstract)；分类 cs.LG

Comments Published as a conference paper at the Sixth International Conference on Learning Representations (ICLR 2018) https://openreview.net/forum?id=SyZI0GWCZ

1801.08019 2018-01-25 cs.LG stat.ML 57%

Training Set Debugging Using Trusted Items

Xuezhou Zhang, Xiaojin Zhu, Stephen J. Wright

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

Comments AAAI 2018

1801.01204 2018-01-08 cs.LG 57%

Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach

Theodora S. Brisimi, Tingting Xu, Taiyao Wang, Wuyang Dai, William G. Adams, Ioannis Ch. Paschalidis

专题命中安全评测：safety(abstract)；分类 cs.LG

1801.01058 2018-01-04 cs.LG 57%

Polynomial-based rotation invariant features

Jarek Duda

专题命中安全评测：alignment(abstract)；分类 cs.LG

Comments 6 pages, 3 figures

1706.03475 2017-09-25 cs.LG stat.ML 57%

Confident Multiple Choice Learning

Kimin Lee, Changho Hwang, KyoungSoo Park, Jinwoo Shin

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

Comments Accepted in ICML 2017

1702.05796 2017-02-21 cs.LG 57%

Collaborative Deep Reinforcement Learning

Kaixiang Lin, Shu Wang, Jiayu Zhou

专题命中安全评测：alignment(abstract)；分类 cs.LG

1604.06963 2016-10-12 cs.AI 57%

Limits to Verification and Validation of Agentic Behavior

David J. Jilk

专题命中安全评测：safety(abstract)；分类 cs.AI

Comments 13 pages, 0 figures

1602.09067 2016-03-01 cs.CY 57%

Firebird: Predicting Fire Risk and Prioritizing Fire Inspections in Atlanta

Michael Madaio, Shang-Tse Chen, Oliver L. Haimson, Wenwen Zhang, Xiang Cheng, Matthew Hinds-Aldrich, Duen Horng Chau, Bistra Dilkina

专题命中安全评测：safety(abstract)；分类 cs.CY

Comments 10 pages, 4 figures, submitted to KDD 2016

1602.02710 2016-02-09 cs.GT cs.AI 57%

Strategic disclosure of opinions on a social network

Umberto Grandi, Emiliano Lorini, Laurent Perrussel

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

1. 安全评测 9434 篇

Risk-Aware Reasoning for Autonomous Vehicles

GRAVITAS: A Model Checking Based Planning and Goal Reasoning Framework for Autonomous Systems

From self-tuning regulators to reinforcement learning and back again

Adversarial Vulnerability Bounds for Gaussian Process Classification

The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition

Engineering problems in machine learning systems

MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks

Rule Applicability on RDF Triplestore Schemas

A unified view on differential privacy and robustness to adversarial examples

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

Multi-modal Discriminative Model for Vision-and-Language Navigation

Predicting Model Failure using Saliency Maps in Autonomous Driving Systems

On the Connection Between Adversarial Robustness and Saliency Map Interpretability

An Evaluation of Bitcoin Address Classification based on Transaction History Summarization

Adversarial Examples - A Complete Characterisation of the Phenomenon

Solving Large Extensive-Form Games with Strategy Constraints

Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures

Unrestricted Adversarial Examples

A Learning-Based Framework for Two-Dimensional Vehicle Maneuver Prediction over V2V Networks

Ensemble learning with Conformal Predictors: Targeting credible predictions of conversion from Mild Cognitive Impairment to Alzheimer's Disease

Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment

Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

Training Set Debugging Using Trusted Items

Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach

Polynomial-based rotation invariant features

Confident Multiple Choice Learning

Collaborative Deep Reinforcement Learning

Limits to Verification and Validation of Agentic Behavior

Firebird: Predicting Fire Risk and Prioritizing Fire Inspections in Atlanta

Strategic disclosure of opinions on a social network