当前大型语言模型（LLM）的安全方法主要关注显性有害内容，而忽视了关键漏洞：无法理解上下文和识别用户意图。这创造了可被恶意用户系统性利用的漏洞。我们通过评估多个最先进的LLM，包括ChatGPT、Claude、Gemini和DeepSeek，发现通过情感框架、逐步揭示和学术辩护技术可以绕过可靠的安全机制。值得注意的是，增强推理的配置反而增强了利用效果，提高了事实准确性但未能探究潜在意图。例外的是Claude Opus 4.1，在某些用例中优先考虑意图检测而非信息提供。这种模式揭示了当前架构设计存在系统性漏洞。这些限制要求向以上下文理解和意图识别为核心的安全能力转变，而非事后防护机制。
英文摘要：
Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities that malicious users can systematically leverage to circumvent safety mechanisms. We empirically evaluate multiple state-of-the-art LLMs, including ChatGPT, Claude, Gemini, and DeepSeek. Our analysis demonstrates the circumvention of reliable safety mechanisms through emotional framing, progressive revelation, and academic justification techniques. Notably, reasoning-enabled configurations amplified rather than mitigated the effectiveness of exploitation, increasing factual precision while failing to interrogate the underlying intent. The exception was Claude Opus 4.1, which prioritized intent detection over information provision in some use cases. This pattern reveals that current architectural designs create systematic vulnerabilities. These limitations require paradigmatic shifts toward contextual understanding and intent recognition as core safety capabilities rather than post-hoc protective mechanisms.
AI-driven Intent-Based Networking Approach for Self-configuration of Next Generation Networks
Information and Computer Science Department, King Fahd University of Petroleum and Minerals（信息与计算机科学系，国王法赫德石油与矿物大学）；IRC for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals（智能安全系统研究院，国王法赫德石油与矿物大学）
Upper limb and hand functionality is critical to many activities of daily living and the amputation of one can lead to significant functionality loss for individuals. From this perspective, advanced prosthetic hands of the future are anticipated to benefit from improved shared control between a robotic hand and its human user, but more importantly from the improved capability to infer human intent from multimodal sensor data to provide the robotic hand perception abilities regarding the operational context. Such multimodal sensor data may include various environment sensors including vision, a…
The AUTOLab at University of California, Berkeley（加州大学伯克利分校AUTOLab实验室）
A new generation of automated bin picking systems using deep learning is evolving to support increasing demand for e-commerce. To accommodate a wide variety of products, many automated systems include multiple gripper types and/or tool changers. However, for some objects, sequential grasp failures are common: when a computed grasp fails to lift and remove the object, the bin is often left unchanged; as the sensor input is consistent, the system retries the same grasp over and over, resulting in a significant reduction in mean successful picks per hour (MPPH). Based on an empirical study of seq…
Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution
University of Liverpool（利物浦大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Zurich University of Applied Science（苏黎世应用科学大学）；Indian Institute of Science（印度科学研究所）；University of Information Technology（信息技术大学）；The University of Tokyo（东京大学）
Honda Research Institute EU（本田欧洲研究院）；Honda R&D Co., Ltd. Innovative Research Excellence（本田研发株式会社创新卓越研究中心）
Shared control can help in teleoperated object manipulation by assisting with the execution of the user's intention. To this end, robust and prompt intention estimation is needed, which relies on behavioral observations. Here, an intention estimation framework is presented, which uses natural gaze and motion features to predict the current action and the target object. The system is trained and tested in a simulated environment with pick and place sequences produced in a relatively cluttered scene and with both hands, with possible hand-over to the other hand. Validation is conducted across di…
