大模型对齐与安全 - arXivDaily 专题

2312.01855 2024-04-03 cs.RO cs.AI 79%

Modular Control Architecture for Safe Marine Navigation: Reinforcement Learning and Predictive Safety Filters

Aksel Vaaler, Svein Jostein Husa, Daniel Menges, Thomas Nakken Larsen, Adil Rasheed

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

Comments 15 pages, 15 figures

2403.14678 2024-03-25 cs.LG 79%

Towards a Framework for Deep Learning Certification in Safety-Critical Applications Using Inherently Safe Design and Run-Time Error Detection

Romeo Valentin

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

Comments Master Thesis

2403.12114 2024-03-20 cs.SE cs.AI 79%

Safety Analysis of Autonomous Railway Systems: An Introduction to the SACRED Methodology

Josh Hunter, John McDermid, Simon Burton

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

Comments S. Bernardi, T. Zoppi (Editors), "Fast Abstracts and Student Forum Proceedings - EDCC 2024 - 19th European Dependable Computing Conference, Leuven, Belgium, 8-11 April 2024"

2402.04182 2024-02-07 cs.LG cs.RO 79%

Reinforcement Learning with Ensemble Model Predictive Safety Certification

Sven Gronauer, Tom Haider, Felippe Schmoeller da Roza, Klaus Diepold

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

Comments Published in: Proc. of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024)

2401.00996 2024-01-03 cs.AI cs.CR cs.SE 79%

Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment

Jie Zhu, Leye Wang, Xiao Han, Anmin Liu, Tao Xie

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

Comments Accepted by IEEE Transactions on Software Engineering (TSE). Camera-ready Version. arXiv admin note: substantial text overlap with arXiv:2208.05969

2309.09919 2023-11-29 cs.RO cs.AI cs.FL 79%

Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents

Ziyi Yang, Shreyas S. Raman, Ankit Shah, Stefanie Tellex

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

2310.19007 2023-11-01 cs.LG 79%

Behavior Alignment via Reward Function Optimization

Dhawal Gupta, Yash Chandak, Scott M. Jordan, Philip S. Thomas, Bruno Castro da Silva

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

Comments (Spotlight) Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)

2309.10657 2023-10-05 cs.RO cs.LG cs.MA cs.SY eess.SY 79%

Learning Adaptive Safety for Multi-Agent Systems

Luigi Berducci, Shuo Yang, Rahul Mangharam, Radu Grosu

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

Comments Update with appendix

2309.08709 2023-09-19 stat.ML cs.LG 79%

Price of Safety in Linear Best Arm Identification

Xuedong Shang, Igor Colin, Merwan Barlier, Hamza Cherkaoui

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

Comments 20 pages, 1 figures

2307.08602 2023-08-15 cs.RO cs.LG cs.MA cs.SY eess.SY math.OC 79%

CaRT: Certified Safety and Robust Tracking in Learning-based Motion Planning for Multi-Agent Systems

Hiroyasu Tsukamoto, Benjamin Rivière, Changrak Choi, Amir Rahmani, Soon-Jo Chung

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

Comments IEEE Conference on Decision and Control (CDC), Preprint Version, Accepted July, 2023

2308.03176 2023-08-08 cs.AI 79%

Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language Processing

Shuang Ao

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

Comments 4 pages

Journal ref 2023

2307.02164 2023-07-06 cs.AI 79%

Safety Shielding under Delayed Observation

Filip Cano Córdoba, Alexander Palmisano, Martin Fränzle, Roderick Bloem, Bettina Könighofer

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

Comments 6 pages, Published at ICAPS 2023 (Main Track)

2210.05596 2023-03-29 eess.SY cs.LG cs.RO cs.SY 79%

Geometry of Radial Basis Neural Networks for Safety Biased Approximation of Unsafe Regions

Ahmad Abuaish, Mohit Srinivasan, Patricio A. Vela

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

Comments Accepted into American Control Conference (ACC) 2023

2303.02386 2023-03-07 cs.RO cs.LG cs.SY eess.SY 79%

Modular Safety-Critical Control of Legged Robots

Berk Tosun, Evren Samur

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

Comments Submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023)

2302.08969 2023-02-20 cs.IT cs.LG math.IT 79%

Deep Reinforcement Learning for mmWave Initial Beam Alignment

Daniel Tandler, Sebastian Dörner, Marc Gauger, Stephan ten Brink

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

2212.06998 2022-12-15 cs.LG cs.RO 79%

Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

Linrui Zhang, Zichen Yan, Li Shen, Shoujie Li, Xueqian Wang, Dacheng Tao

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

Comments The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

2204.07874 2022-12-07 cs.SE cs.LG 79%

Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System

Markus Borg, Jens Henriksson, Kasper Socha, Olof Lennartsson, Elias Sonnsjö Lönegren, Thanh Bui, Piotr Tomaszewski, Sankar Raman Sathyamoorthy, Sebastian Brink, Mahshid Helali Moghadam

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

Comments Accepted for publication in Software Quality Journal

2211.01498 2022-11-04 cs.LG stat.ML 79%

On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Dennis Wei, Rahul Nair, Amit Dhurandhar, Kush R. Varshney, Elizabeth M. Daly, Moninder Singh

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

Comments Published at NeurIPS 2022

2201.05077 2022-10-17 cs.SE cs.LG 79%

Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering

Mohammed Oualid Attaoui, Hazem Fahmy, Fabrizio Pastore, Lionel Briand

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

Comments 41 pages, 12 figures, 15 tables

2208.05969 2022-09-12 cs.LG cs.CR cs.SE 79%

Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment

Jie Zhu, Leye Wang, Xiao Han

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

Comments Accepted by ASE2022. Camera-ready Version

2208.04803 2022-08-10 cs.LG cs.RO 79%

Exploring the trade off between human driving imitation and safety for traffic simulation

Yann Koeberle, Stefano Sabatini, Dzmitry Tsishkou, Christophe Sabourin

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

2012.07369 2022-07-25 cs.LG cs.SY eess.SY math.OC 79%

Learning for MPC with Stability & Safety Guarantees

Sébastien Gros, Mario Zanon

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

2206.00886 2022-06-03 cs.RO cs.LG 79%

Watch Out for the Safety-Threatening Actors: Proactively Mitigating Safety Hazards

Saurabh Jha, Shengkun Cui, Zbigniew Kalbarczyk, Ravishankar K. Iyer

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

2205.01419 2022-05-04 cs.RO cs.CV cs.FL cs.LG cs.SY eess.SY 79%

An Empirical Analysis of the Use of Real-Time Reachability for the Safety Assurance of Autonomous Vehicles

Patrick Musau, Nathaniel Hamilton, Diego Manzanas Lopez, Preston Robinette, Taylor T. Johnson

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

Comments 30 pages, 12 Figures, Submitted to Artificial Intelligence's Special Issue on "Risk-Aware Autonomous Systems: Theory and Practice."

2107.12045 2022-04-15 cs.LG cs.SE 79%

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Florian Tambon, Gabriel Laberge, Le An, Amin Nikanjam, Paulina Stevia Nouwou Mindom, Yann Pequignot, Foutse Khomh, Giulio Antoniol, Ettore Merlo, François Laviolette

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

Comments 60 pages (92 pages with references and complements), submitted to a journal (Automated Software Engineering). Changes: Emphasizing difference traditional software engineering / ML approach. Adding Related Works, Threats to Validity and Complementary Materials. Adding a table listing papers reference for each section/subsections

Journal ref Autom Softw Eng 29, 38 (2022)

2112.05135 2022-03-30 cs.LG cs.CV 79%

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures

Dan Hendrycks, Andy Zou, Mantas Mazeika, Leonard Tang, Bo Li, Dawn Song, Jacob Steinhardt

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

Comments CVPR 2022. Code and models are available at https://github.com/andyzoujm/pixmix

2105.02331 2022-02-22 cs.AI 79%

Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance

Wei Guo, Marc Brittain, Peng Wei

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

2202.01781 2022-02-07 cs.CV cs.AI 79%

Predicting the impact of urban change in pedestrian and road safety

Cristina Bustos, Daniel Rhoads, Agata Lapedriza, Javier Borge-Holthoefer, Albert Solé-Ribalta

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

2112.12210 2021-12-30 cs.LG cs.SY eess.SY 79%

ProBF: Learning Probabilistic Safety Certificates with Barrier Functions

Athindran Ramesh Kumar, Sulin Liu, Jaime F. Fisac, Ryan P. Adams, Peter J. Ramadge

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

Comments Presented at NeurIPS 2021 workshop - Safe and Robust Control of Uncertain Systems

2111.14324 2021-11-30 cs.LG 79%

Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey

Mehrnoosh Askarpour, Alan Wassyng, Mark Lawford, Richard Paige, Zinovy Diskin

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

1. 安全训练 3288 篇

Modular Control Architecture for Safe Marine Navigation: Reinforcement Learning and Predictive Safety Filters

Towards a Framework for Deep Learning Certification in Safety-Critical Applications Using Inherently Safe Design and Run-Time Error Detection

Safety Analysis of Autonomous Railway Systems: An Introduction to the SACRED Methodology

Reinforcement Learning with Ensemble Model Predictive Safety Certification

Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment

Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents

Behavior Alignment via Reward Function Optimization

Learning Adaptive Safety for Multi-Agent Systems

Price of Safety in Linear Best Arm Identification

CaRT: Certified Safety and Robust Tracking in Learning-based Motion Planning for Multi-Agent Systems

Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language Processing

Safety Shielding under Delayed Observation

Geometry of Radial Basis Neural Networks for Safety Biased Approximation of Unsafe Regions

Modular Safety-Critical Control of Legged Robots

Deep Reinforcement Learning for mmWave Initial Beam Alignment

Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System

On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering

Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment

Exploring the trade off between human driving imitation and safety for traffic simulation

Learning for MPC with Stability & Safety Guarantees

Watch Out for the Safety-Threatening Actors: Proactively Mitigating Safety Hazards

An Empirical Analysis of the Use of Real-Time Reachability for the Safety Assurance of Autonomous Vehicles

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures

Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance

Predicting the impact of urban change in pedestrian and road safety

ProBF: Learning Probabilistic Safety Certificates with Barrier Functions

Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey