arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

共收录 8095 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 8095 篇

2110.00627 2021-12-07 cs.LG cs.CC stat.AP 57%

On the complexity of the optimal transport problem with graph-structured cost

Jiaojiao Fan, Isabel Haasler, Johan Karlsson, Yongxin Chen

专题命中 其他安全 :alignment(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.15353 2021-12-03 eess.SP cs.LG 57%

Patient-independent Schizophrenia Relapse Prediction Using Mobile Sensor based Daily Behavioral Rhythm Changes

Bishal Lamichhane, Dror Ben-Zeev, Andrew Campbell, Tanzeem Choudhury, Marta Hauser, John Kane, Mikio Obuchi, Emily Scherer, Megan Walsh, Rui Wang, Weichen Wang, Akane Sano

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments EAI MobiHealth 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
1906.01820 2021-12-02 cs.AI 57%

Risks from Learned Optimization in Advanced Machine Learning Systems

Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, Scott Garrabrant

专题命中 其他安全 :safety(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.15622 2021-12-01 cs.CL 57%

Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Approaches

Virginia Adams, Hoo-Chang Shin, Carol Anderson, Bo Liu, Anas Abidin

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments Submission to the BioCreative VII challenge - Track-2

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.15101 2021-12-01 cs.LG physics.comp-ph physics.med-ph 57%

A novel data-driven algorithm to predict anomalous prescription based on patient's feature set

Qiongge Li, Jean Wright, Russell Hales, Ranh Voong, Todd McNutt

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.14977 2021-12-01 eess.SY cs.CL cs.SY eess.SP 57%

A Natural Language Processing and Deep Learning based Model for Automated Vehicle Diagnostics using Free-Text Customer Service Reports

Ali Khodadadi, Soroush Ghandiparsi, Chen-Nee Chuah

专题命中 其他安全 :safety(abstract);分类 cs.CL

Comments 24 page, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.14598 2021-11-30 cs.LG cs.MA cs.RO 57%

Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning

Ralvi Isufaj, Marsel Omeri, Miquel Angel Piera

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments 14 pages, 5 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.13350 2021-11-29 cs.LG cs.CV cs.RO 57%

Jointly Learning Agent and Lane Information for Multimodal Trajectory Prediction

Jie Wang, Caili Guo, Minan Guo, Jiujiu Chen

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2109.02529 2021-11-22 cs.AI cs.RO 57%

ViSTA: a Framework for Virtual Scenario-based Testing of Autonomous Vehicles

Andrea Piazzoni, Jim Cherian, Mohamed Azhar, Jing Yew Yap, James Lee Wei Shung, Roshan Vijay

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments Accepted at 2021 IEEE Autonomous Driving AI Test Challenge - AITest 2021 8 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.04248 2021-11-09 cs.AI cs.MA 57%

Trust-aware Control for Intelligent Transportation Systems

Mingxi Cheng, Junyao Zhang, Shahin Nazarian, Jyotirmoy Deshmukh, Paul Bogdan

专题命中 其他安全 :safety(abstract);分类 cs.AI

Journal ref Cheng,M., Zhang, J., Nazarian, S., Deshmukh, J. & Bogdan, P., Trust-aware Control for Intelligent Transportation Systemsin, in Proceedings of the 32th IEEE Intelligent Vehicle Symposium(2021)

详情

展开后加载摘要…

URL PDF HTML 收藏
2111.03511 2021-11-08 cs.HC cs.CL cs.RO 57%

Disengagement Cause-and-Effect Relationships Extraction Using an NLP Pipeline

Yangtao Zhang, X. Jessie Yang, Feng Zhou

专题命中 其他安全 :safety(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2108.10851 2021-11-02 cs.AI cs.SE 57%

Autoencoder-based Semantic Novelty Detection: Towards Dependable AI-based Systems

Andreas Rausch, Azarmidokht Motamedi Sedeh, Meng Zhang

专题命中 其他安全 :safety(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.15245 2021-10-29 cs.RO cs.LG 57%

From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence

Nicholas Roy, Ingmar Posner, Tim Barfoot, Philippe Beaudoin, Yoshua Bengio, Jeannette Bohg, Oliver Brock, Isabelle Depatie, Dieter Fox, Dan Koditschek, Tomas Lozano-Perez, Vikash Mansinghka, Christopher Pal, Blake Richards, Dorsa Sadigh, Stefan Schaal, Gaurav Sukhatme, Denis Therien, Marc Toussaint, Michiel Van de Panne

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.14944 2021-10-29 cs.CV cs.AI 57%

Dispensed Transformer Network for Unsupervised Domain Adaptation

Yunxiang Li, Jingxiong Li, Ruilong Dan, Shuai Wang, Kai Jin, Guodong Zeng, Jun Wang, Xiangji Pan, Qianni Zhang, Huiyu Zhou, Qun Jin, Li Wang, Yaqi Wang

专题命中 其他安全 :alignment(abstract);分类 cs.AI

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2109.11690 2021-10-28 cs.HC cs.LG 57%

Discovering and Validating AI Errors With Crowdsourced Failure Reports

Ángel Alexander Cabrera, Abraham J. Druck, Jason I. Hong, Adam Perer

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.13585 2021-10-27 cs.LG eess.SP 57%

Concepts for Automated Machine Learning in Smart Grid Applications

Stefan Meisenbacher, Janik Pinter, Tim Martin, Veit Hagenmeyer, Ralf Mikut

专题命中 其他安全 :alignment(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.12586 2021-10-26 cs.SE cs.AI cs.MA 57%

Complete Agent-driven Model-based System Testing for Autonomous Systems

Kerstin I. Eder, Wen-ling Huang, Jan Peleska

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments In Proceedings FMAS 2021, arXiv:2110.11527

Journal ref EPTCS 348, 2021, pp. 54-72

详情

展开后加载摘要…

URL PDF HTML 收藏
1712.01145 2021-10-19 cs.CR cs.LG stat.ML 57%

Learning Fast and Slow: PROPEDEUTICA for Real-time Malware Detection

Ruimin Sun, Xiaoyong Yuan, Pan He, Qile Zhu, Aokun Chen, Andre Gregio, Daniela Oliveira, Xiaolin Li

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments 12 pages, 4 figures. This paper has been accepted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.07729 2021-10-18 cs.AI cs.RO 57%

An Independent Study of Reinforcement Learning and Autonomous Driving

Hanzhi Yang

专题命中 其他安全 :safety(abstract);分类 cs.AI

Comments 32 pages in total, 7 figures, 3 appendices, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.07382 2021-10-15 cs.CL 57%

Transferring Semantic Knowledge Into Language Encoders

Mohammad Umair, Francis Ferraro

专题命中 其他安全 :alignment(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.06624 2021-10-14 cs.LG cs.NA math.NA 57%

Identification of Metallic Objects using Spectral Magnetic Polarizability Tensor Signatures: Object Classification

B. A. Wilson, P. D. Ledger, W. R. B. Lionheart

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2103.05524 2021-10-13 cs.LG cond-mat.dis-nn stat.ML 57%

On the interplay between data structure and loss function in classification problems

Stéphane d'Ascoli, Marylou Gabrié, Levent Sagun, Giulio Biroli

专题命中 其他安全 :alignment(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.04923 2021-10-12 cs.LG cs.SD eess.AS 57%

Crack detection using tap-testing and machine learning techniques to prevent potential rockfall incidents

Roya Nasimi, Fernando Moreu, John Stormont

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.04502 2021-10-12 cs.LG 57%

EnsembleNTLDetect: An Intelligent Framework for Electricity Theft Detection in Smart Grid

Yogesh Kulkarni, Sayf Hussain Z, Krithi Ramamritham, Nivethitha Somu

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments Accepted at the 2nd Workshop on Large-scale Industrial Time Series Analysis at the 21st IEEE International Conference on Data Mining (ICDM), 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.04192 2021-10-11 cs.RO cs.AI cs.HC 57%

Explaining Reward Functions to Humans for Better Human-Robot Collaboration

Lindsay Sanneman, Julie Shah

专题命中 其他安全 :alignment(abstract);分类 cs.AI

Comments Presented at AI-HRI symposium as part of AAAI-FSS 2021 (arXiv:2109.10836)

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.04005 2021-10-11 eess.AS cs.LG cs.SD 57%

KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms

Chien-Feng Liao, Jen-Yu Liu, Yi-Hsuan Yang

专题命中 其他安全 :alignment(abstract);分类 cs.LG

Comments Submitted to ICASSP 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2102.05917 2021-09-27 cs.LG 57%

PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification

Dominique Mercier, Andreas Dengel, Sheraz Ahmed

专题命中 其他安全 :safety(abstract);分类 cs.LG

Comments 8 pages, 8 figures, 6 tables, submitted to IJCNN 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2109.06129 2021-09-15 cs.CV cs.CL 57%

Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color

Mostafa Abdou, Artur Kulmizev, Daniel Hershcovich, Stella Frank, Ellie Pavlick, Anders Søgaard

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments CoNLL 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2109.00859 2021-09-03 cs.CL cs.PL 57%

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation

Yue Wang, Weishi Wang, Shafiq Joty, Steven C. H. Hoi

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments Accepted to EMNLP 2021. 13 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2109.00253 2021-09-02 cs.CL cs.IR 57%

Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast

Liang Wang, Wei Zhao, Jingming Liu

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments Accepted to EMNLP 2021 main conference

详情

展开后加载摘要…

URL PDF HTML 收藏