Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with real-world actuation introduce a new vulnerability: instructions that appear semantically benign may still lead to dangerous real-world consequences, revealing a fundamental misalignment between linguistic security and physical outcomes. In this paper, we introduce Blindfold, an automated attack framework that leverages the limited causal reasoning capabilities of embodied LLMs in real-world action contexts. Rather than iterative trial-and-error jailbreaking of black-box embodied LLMs, Blindfold adopts an Adversarial Proxy Planning strategy: it compromises a local surrogate LLM to perform action-level manipulations that appear semantically safe but could result in harmful physical effects when executed. Blindfold further conceals key malicious actions by injecting carefully crafted noise to evade detection by defense mechanisms, and it incorporates a rule-based verifier to improve the attack executability. Evaluations on both embodied AI simulators and a real-world 6DoF robotic arm show that Blindfold achieves up to 53% higher attack success rates than SOTA baselines, highlighting the urgent need to move beyond surface-level language censorship and toward consequence-aware defense mechanisms to secure embodied LLMs.
A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI
Department of Computer Science, City University of Hong Kong(城市大学计算机科学系);School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电子与电气工程学院);Department of Informatics, Universität Hamburg(汉堡大学信息学院)
CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding
JD Explore Academy(京东探索研究院);School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);South China University of Technology(华南理工大学);Sun Yat-sen University(中山大学);School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)人工智能学院)
Tsinghua University(清华大学);Pengcheng Laboratory(鹏城实验室);Xiaomi EV(小米电动车);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Peking University(北京大学);HKUST(GZ)(香港科技大学(广州))
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);AiRiA;Nanjing University of Information Science and Technology(南京信息科学技术大学)
BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation
Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education, East China University of Science and Technology, Shanghai, CN(能源化工过程智能制造教育部重点实验室,东华大学,上海,中国);Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, CN(东华大学计算机科学与工程系,上海,中国);Department of Laboratory Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, CN(复旦大学附属瑞金医院检验医学科,上海,中国);School of Information Science and Technology, Shihezi University, Shihezi, CN(石河子大学信息科学与技术学院,石河子,中国)
SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Department of Automation, Tsinghua University(清华大学自动化系);Nanyang Technological University(南洋理工大学);Beijing Normal University(北京师范大学)
TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation
School of Computing, National University of Singapore(新加坡国立大学计算机学院);School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院)
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(北京大学计算机学院多媒体信息处理国家重点实验室);EvoPhys AI(EvoPhys人工智能公司);Joy Future Academy, JD(京东探索研究院);The University of Sydney(悉尼大学);The Hong Kong University of Science and Technology(香港科技大学);Beijing Institute of Technology(北京理工大学)
Octopus: Embodied Vision-Language Programmer from Environmental Feedback
S-Lab, Nanyang Technological University(新加坡南洋理工大学S-Lab);Shanghai AI Laboratory(上海人工智能实验室);Tsinghua University(清华大学);BUPT(北京邮电大学);XJTU(西安交通大学);Hong Kong Baptist University(香港浸会大学)
EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems
School of Software, Harbin Institute of Technology(哈尔滨工业大学软件学院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院);School of Mathematical and Computer Sciences, Heriot-Watt University, Malaysia Campus(赫瑞-瓦特大学马来西亚校区数学与计算机科学学院);School of Future Science and Engineering, Soochow University(苏州大学未来科学与工程学院)
EnvBridge: Bridging Diverse Environments with Cross-Environment Knowledge Transfer for Embodied AI
Panasonic Connect Co., Ltd.(松下连接有限公司);National University of Singapore(新加坡国立大学);Panasonic R&D Center Singapore(松下新加坡研发中心);Panasonic R&D Center Germany(松下德国研发中心)
EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation
Beihang University(北京航空航天大学);Zhongguancun Academy(中关村学院);University of Science and Technology of China(中国科学技术大学);National University of Singapore(新加坡国立大学);CASIA, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所(CASIA));Microsoft Research Asia(微软亚洲研究院)
EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model
University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Institute of Automation, Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所);New Laboratory of Pattern Recognition (NLPR)(模式识别新实验室);State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)(多模态人工智能系统国家重点实验室);Beihang University(北航);Chinese University of Hong Kong(香港大学)
EHC-MM: Embodied Holistic Control for Mobile Manipulation
Beijing Samsung Telecom R&D Center(北京三星通信技术研发中心);National Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室);School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);PKU-WUHAN Institute for Artificial Intelligence(北京大学-武汉人工智能研究院);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Tsinghua University(清华大学);Beijing University of Posts and Telecommunications(北京邮电大学)
LaGEA: Language Guided Embodied Agents for Robotic Manipulation
Department of Robotics;Mechatronics Engineering, University of Dhaka, Bangladesh;Center for Computational \& Data Sciences, Independent University, Bangladesh