As artificial intelligence extends beyond digital interfaces into cars, drones, and collaborative robots, a new survey published in Machine Intelligence Research examines the security and ethical risks when vision-language models guide physical actions. The review, conducted by researchers from the Institute of Automation of the Chinese Academy of Sciences, University College London, Minzu University of China, and the China Academy of Electronics and Information Technology, maps how failures in perception, planning, instruction following, and human-robot interaction can lead to unsafe outcomes.
Vision-language models (VLMs) connect images with text, while vision-language-action models (VLAs) extend this to robot plans and control signals. This integration enables natural-language instruction and flexible task execution, but it also creates a chain of dependency. Flawed data can distort perception, weak alignment can produce hallucinations, and malicious inputs can redirect decisions. In a chatbot, such errors may generate misinformation; in an autonomous vehicle or industrial robot, they may lead to collisions or damaged equipment. Existing safeguards are often benchmark-specific and fragmented, necessitating deeper research into unified, adaptive defenses.
The survey, published on July 13, 2026, with DOI 10.1007/s11633-025-1626-x, organizes the major threats and countermeasures. Threats include hallucinations, synthetic forgeries, adversarial attacks, privacy leakage, and unsafe execution. Defenses span contextual checking, forgery detection, privacy protection, and risk-aware reasoning. The authors emphasize that no single filter can secure an embodied agent; protection must follow the entire path from sensor input to physical execution.
“The central challenge is not simply making models more accurate, but ensuring that a system remains safe when its sensors, language inputs, and operating conditions are imperfect,” the authors state. They advocate for combined defenses, transparent risk metrics, continuous monitoring, and human oversight for critical decisions. A trustworthy robot must explain its actions, recognize uncertainty, and fall back safely.
For developers and regulators, the survey provides a practical checklist for evaluating embodied systems before deployment. Future platforms could combine interpretable reasoning, attack detection, privacy-preserving computation, and dynamic safety controls under reproducible protocols. This approach could support safer autonomous transport, healthcare assistance, warehouse automation, and collaborative robotics while making responsibility easier to trace.
The review also warns that strong laboratory results may not transfer to noisy, culturally diverse, and resource-constrained environments. Progress depends on cross-disciplinary cooperation and testing that measures not only task success but safe behavior under stress. The work was partially funded by the National Natural Science Foundation of China and the Engineering and Physical Sciences Research Council (EPSRC) in the UK.
