"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
“不要向用户提及此事”:检测与理解恶意代理技能
Yi Liu, Zhihao Chen, Yanjun Zhang, Gelei Deng, Yuekang Li, Jianting Ning, Leo Yu Zhang
机构
*
Griffith University(格里菲斯大学)
;
Nanyang Technological University(南洋理工大学)
;
University of New South Wales(新南威尔士大学)
;
Zhejiang Key Laboratory of Digital Fashion and Data Governance, Zhejiang Sci-Tech University(浙江数字时尚与数据治理重点实验室,浙江科技大学)
Cross-Modal Benchmarking for Robotic Perception in Natural Environments
自然环境中机器人感知的跨模态基准测试
David Hall, Joshua Knights, Mark Cox, Peyman Moghadam
机构
*
CSIRO Robotics, CSIRO, Australia(CSIRO机器人研究所,CSIRO,澳大利亚)
;
University of Sydney (USyd), Australia(悉尼大学(USyd),澳大利亚)
;
Queensland University of Technology (QUT), Australia(昆士兰理工大学(QUT),澳大利亚)
Comments49 pages, 13 figures. Version 3: Revised in response to the JCAP editor's report. Added Section 3.2.12 on the treatment of nuisance parameters in the evidence and tension calculations. Results unchanged
机构
*
School of Computer Science, Wuhan University(武汉大学计算机学院)
;
School of Computer Science, Central China Normal University(中央师范大学计算机学院)
;
School of Computing Technologies, RMIT University(皇家墨尔本理工大学计算技术学院)