大模型对齐与安全

ReMatch: Retrieval Enhanced Schema Matching with LLMs

Eitam Sheetrit, Menachem Brief, Moshik Mishaeli, Oren Elisha

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ

Jonas Belouadi, Anne Lauscher, Steffen Eger

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL

Comments Accepted at ICLR 2024 (poster); Project Page: https://github.com/potamides/AutomaTikZ

Journal ref The Twelfth International Conference on Learning Representations, 2024

Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels

Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan, Christopher G. Brinton

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Comments 16 pages, 11 figures

AI Knowledge and Reasoning: Emulating Expert Creativity in Scientific Research

Anirban Mukherjee, Hannah Hanwen Chang

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models

Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Security Risks Concerns of Generative AI in the IoT

Honghui Xu, Yingshu Li, Olusesi Balogun, Shaoen Wu, Yue Wang, Zhipeng Cai

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Comments 6 pages, 2 figures

Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective

Subhodip Panda, Shashwat Sourav, Prathosh A. P

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Blockchain-based Pseudonym Management for Vehicle Twin Migrations in Vehicular Edge Metaverse

Jiawen Kang, Xiaofeng Luo, Jiangtian Nie, Tianhao Wu, Haibo Zhou, Yonghua Wang, Dusit Niyato, Shiwen Mao, Shengli Xie

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments 14 pages, 9 figures

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye, Shruti Tople

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Comments To appear in the Proceedings on Privacy Enhancing Technologies (PoPETs 2024)

Consensus learning: A novel decentralised ensemble learning paradigm

Horia Magureanu, Naïri Usher

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments 27 pages plus appendices, 8 figures

FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph Completion

Wei Tang, Zhiqian Wu, Yixin Cao, Yong Liao, Pengyuan Zhou

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL

Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing

Andy Li, Milan Markovic, Peter Edwards, Georgios Leontidis

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments 31 pages, 4 figures, 4 tables

Journal ref Expert Systems with Applications 2023

Decentralized Energy Marketplace via NFTs and AI-based Agents

Rasoul Nikbakht, Farhana Javed, Farhad Rezazadeh, Nikolaos Bartzoudis, Josep Mangues-Bafalluy

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Comments 6 pages

Private Graph Extraction via Feature Explanations

Iyiola E. Olatunji, Mandeep Rathee, Thorben Funke, Megha Khosla

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.LG

Comments Accepted at PETS 2023

Journal ref Proceedings of the 23rd Privacy Enhancing Technologies Symposium (PETS), 2023

Multi-step Jailbreaking Privacy Attacks on ChatGPT

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, Yangqiu Song

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL

Comments Findings of EMNLP 2023. Updated with results on open-source LLMs

RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents

Yubo Shu, Haonan Zhang, Hansu Gu, Peng Zhang, Tun Lu, Dongsheng Li, Ning Gu

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI

Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training

Ruiqi Xu, Yongfeng Huang, Xin Chen, Lin Zhang

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL

ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning

Linkang Du, Min Chen, Mingyang Sun, Shouling Ji, Peng Cheng, Jiming Chen, Zhikun Zhang

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments To appear in the Network and Distributed System Security Symposium (NDSS) 2024, San Diego, CA, USA

Assessing Trust in Construction AI-Powered Collaborative Robots using Structural Equation Modeling

Newsha Emaminejad, Lisa Kath, Reza Akhavian

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

The Prospect of Enhancing Large-Scale Heterogeneous Federated Learning with Transformers

Yulan Gao, Zhaoxiang Hou, Chengyi Yang, Zengxiang Li, Han Yu

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Learning as a Service

Zilinghan Li, Shilan He, Pranshu Chaturvedi, Trung-Hieu Hoang, Minseok Ryu, E. A. Huerta, Volodymyr Kindratenko, Jordan Fuhrman, Maryellen Giger, Ryan Chard, Kibaek Kim, Ravi Madduri

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.LG

Non-Convex Optimizations for Machine Learning with Theoretical Guarantee: Robust Matrix Completion and Neural Network Learning

Shuai Zhang

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments PhD thesis

FedPower: Privacy-Preserving Distributed Eigenspace Estimation

Xiao Guo, Xiang Li, Xiangyu Chang, Shusen Wang, Zhihua Zhang

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.LG

Distributed Trust Through the Lens of Software Architecture

Sin Kit Lo, Yue Liu, Guangsheng Yu, Qinghua Lu, Xiwei Xu, Liming Zhu

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.AI

FL-Market: Trading Private Models in Federated Learning

Shuyuan Zheng, Yang Cao, Masatoshi Yoshikawa, Huizhong Li, Qiang Yan

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.LG

Comments Extended report for our IEEE BigData 2022 paper

Journal ref Proceedings of the 2022 IEEE International Conference on Big Data, 1525-1534. (https://ieeexplore.ieee.org/document/10020232)

Towards Decentralized Predictive Quality of Service in Next-Generation Vehicular Networks

Filippo Bragato, Tommaso Lotta, Gianmaria Ventura, Matteo Drago, Federico Mason, Marco Giordani, Michele Zorzi

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI

Comments This paper has been accepted for publication at IEEE Information Theory and Applications Workshop (ITA), 2023

Federated Learning -- Methods, Applications and beyond

Moritz Heusinger, Christoph Raab, Fabrice Rossi, Frank-Michael Schleif

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.LG

Journal ref ESANN 2021 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Oct 2021, Online event (Bruges), Belgium. pp.1-10

Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attacks

Jan Aalmoes, Vasisht Duddu, Antoine Boutet

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.LG

Comments The paper's results and conclusions underwent significant changes. The updated paper can be found at arXiv:2211.10209

Privacy and Transparency in Graph Machine Learning: A Unified Perspective

Megha Khosla

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.LG

Comments In Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI) at International Conference on Information and Knowledge Management (CIKM'22)

Targeted Honeyword Generation with Language Models

Fangyi Yu, Miguel Vargas Martin

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.AI

Comments 8 pages, 7 tables, 2 figures