大模型对齐与安全

Attention-Based Scattering Network for Satellite Imagery

Jason Stock, Chuck Anderson

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

Comments NeurIPS 2022 Workshop - Tackling Climate Change with Machine Learning, 4 page limit w/ appendix

Target-aware Molecular Graph Generation

Cheng Tan, Zhangyang Gao, Stan Z. Li

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments Accepted by the 2nd AI4Science Workshop at the 39th International Conference on Machine Learning (ICML), 2022

Good AI for Good: How AI Strategies of the Nordic Countries Address the Sustainable Development Goals

Andreas Theodorou, Juan Carlos Nieves, Virginia Dignum

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

Comments IJCAI-AIofAI 2022 : 2nd Workshop on Adverse Impacts and Collateral Effects of AI Technologies

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

Jingkang Yang, Pengyun Wang, Dejian Zou, Zitang Zhou, Kunyuan Ding, Wenxuan Peng, Haoqi Wang, Guangyao Chen, Bo Li, Yiyou Sun, Xuefeng Du, Kaiyang Zhou, Wayne Zhang, Dan Hendrycks, Yixuan Li, Ziwei Liu

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted by NeurIPS 2022 Datasets and Benchmarks Track. Codebase: https://github.com/Jingkang50/OpenOOD

Mind's Eye: Grounded Language Model Reasoning through Simulation

Ruibo Liu, Jason Wei, Shixiang Shane Gu, Te-Yen Wu, Soroush Vosoughi, Claire Cui, Denny Zhou, Andrew M. Dai

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Local Interpretable Model Agnostic Shap Explanations for machine learning models

P. Sai Ram Aditya, Mayukha Pal

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

Comments Under review

Unified Probabilistic Neural Architecture and Weight Ensembling Improves Model Robustness

Sumegha Premchandar, Sandeep Madireddy, Sanket Jantre, Prasanna Balaprakash

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Reward Learning with Trees: Methods and Evaluation

Tom Bewley, Jonathan Lawry, Arthur Richards, Rachel Craddock, Ian Henderson

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments 22 pages (9 main body). Preprint, under review

Establishing Meta-Decision-Making for AI: An Ontology of Relevance, Representation and Reasoning

Cosmin Badea, Leilani Gilpin

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.CY

Comments This version was peer-reviewed, accepted and presented as part of the AAAI 2021 Fall Symposium FSS-21. 2021

Multi-AI Complex Systems in Humanitarian Response

Joseph Aylett-Bullock, Miguel Luengo-Oroz

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

Comments 8 pages, 1 figure

Journal ref Proceedings of the 3rd KDD Workshop on Data-driven Humanitarian Mapping, 2022, Washington, DC USA

Shifts 2.0: Extending The Dataset of Real Distributional Shifts

Andrey Malinin, Andreas Athanasopoulos, Muhamed Barakovic, Meritxell Bach Cuadra, Mark J. F. Gales, Cristina Granziera, Mara Graziani, Nikolay Kartashev, Konstantinos Kyriakopoulos, Po-Jui Lu, Nataliia Molchanova, Antonis Nikitakis, Vatsal Raina, Francesco La Rosa, Eli Sivena, Vasileios Tsarsitalidis, Efi Tsompopoulou, Elena Volf

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Towards Benchmarking Explainable Artificial Intelligence Methods

Lars Holmberg

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

Comments 13 pages

GreenDB -- A Dataset and Benchmark for Extraction of Sustainability Information of Consumer Goods

Sebastian Jäger, Alexander Flick, Jessica Adriana Sanchez Garcia, Kaspar von den Driesch, Karl Brendel, Felix Biessmann

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

Comments Presented at DataPerf Workshop at the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, 2022

CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks

Mikhail Pautov, Nurislam Tursynbek, Marina Munkhoeva, Nikita Muravev, Aleksandr Petiushko, Ivan Oseledets

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments In Proceedings of AAAI-22, the Thirty-Sixth AAAI Conference on Artificial Intelligence

Journal ref 36 AAAI Conference on Artificial Intelligence AAAI-2022

From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process

Lukas Klein, Mennatallah El-Assady, Paul F. Jäger

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted at IJCAI 2022 Workshop on Explainable Artificial Intelligence (XAI)

PRoA: A Probabilistic Robustness Assessment against Functional Perturbations

Tianle Zhang, Wenjie Ruan, Jonathan E. Fieldsend

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments The short version of this work will appear in the Proceedings of the 2022 European Conference on Machine Learning and Data Mining (ECML-PKDD 2022)

Why we do need Explainable AI for Healthcare

Giovanni Cinà, Tabea Röber, Rob Goedhart, Ilker Birbil

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

Should Social Robots in Retail Manipulate Customers?

Oliver Bendel, Liliana Margarida Dos Santos Alves

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

Comments Accepted paper of the AAAI 2022 Spring Symposium "How Fair is Fair? Achieving Wellbeing AI" (Stanford University)

Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction

Rongzhi Zhang, Rebecca West, Xiquan Cui, Chao Zhang

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

Comments KDD 2022 Applied Data Science Track

Evaluating Automated Driving Planner Robustness against Adversarial Influence

Andres Molina-Markham, Silvia G. Ionescu, Erin Lanus, Derek Ng, Sam Sommerer, Joseph J. Rushanan

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments To appear at the 2022 Workshop on Deception Against Planning Systems and Planning in Adversarial Conditions (DAPSPAC)

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Antonia Creswell, Murray Shanahan, Irina Higgins

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.AI

Unsupervised Driving Behavior Analysis using Representation Learning and Exploiting Group-based Training

Soma Bandyopadhyay, Anish Datta, Shruti Sachan, Arpan Pal

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 7 figures, 8 pages , 7 tables, accepted and presented conference AAAI 2022 AI for Transportation Workshop (Prefinal version)

Search-Based Testing of Reinforcement Learning

Martin Tappler, Filip Cano Córdoba, Bernhard K. Aichernig, Bettina Könighofer

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 11 pages, 15 figures, Accepted at IJCAI-ECAI 2022 (Main Track)

Knowledge Distillation of Russian Language Models with Reduction of Vocabulary

Alina Kolesnikova, Yuri Kuratov, Vasily Konovalov, Mikhail Burtsev

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.LG

Aligning to Social Norms and Values in Interactive Narratives

Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin Choi

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments In Proceedings of NAACL-2022

Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems

Xugui Zhou, Maxfield Kouzel, Homa Alemzadeh

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 10 figures, to appear in the 5th IEEE/IFIP DSN Workshop on Dependable and Secure Machine Learning (DSN-DSML)

Extended Parallel Corpus for Amharic-English Machine Translation

Andargachew Mekonnen Gezmu, Andreas Nürnberger, Tesfaye Bayu Bati

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted to LREC 2022

Data-driven emotional body language generation for social robotics

Mina Marmpena, Fernando Garcia, Angelica Lim, Nikolas Hemion, Thomas Wennekers

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

Comments For the associated video of the generated animations, see https://youtu.be/wmLT8FARSk0 and for a repository of the training data, see https://github.com/minamar/rebl-pepper-data

Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning

Jun Guo, Yonghong Chen, Yihang Hao, Zixin Yin, Yin Yu, Simin Li

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

Blockchain as an Enabler for Transfer Learning in Smart Environments

Amin Anjomshoaa, Edward Curry

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