Related papers: Propagating Unsafe Actions in LLM Controlled Multi…
Teleoperated quadruped robots are increasingly deployed in safety-critical missions -- industrial inspection, military reconnaissance, and emergency response -- yet the security of their communication and control infrastructure remains…
Large language models (LLMs) represent significant breakthroughs in artificial intelligence and hold potential for applications within smart grids. However, as demonstrated in previous literature, AI technologies are susceptible to various…
Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary…
The human ability to learn, generalize, and control complex manipulation tasks through multi-modality feedback suggests a unique capability, which we refer to as dexterity intelligence. Understanding and assessing this intelligence is a…
Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) services due to their exceptional proficiency in understanding and generating human-like text. LLM chatbots, in particular, have seen widespread adoption,…
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…
The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric environments. However, EAI systems introduce critical security…
We introduce a novel framework for automatic behavior tree (BT) construction in heterogeneous multi-robot systems, designed to address the challenges of adaptability and robustness in dynamic environments. Traditional robots are limited by…
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…
Recently, there has been extensive study of cooperative multi-agent multi-armed bandits where a set of distributed agents cooperatively play the same multi-armed bandit game. The goal is to develop bandit algorithms with the optimal group…
Recent research has demonstrated the potential of reinforcement learning in effective multi-robot collaboration, particularly in social dilemmas where robots face a trade-off between self-interest and collective benefits. However,…
Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…
Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world. When agents can only partially observe their…
Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…
Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…
Shared autonomy methods, where a human operator and a robot arm work together, have enabled robots to complete a range of complex and highly variable tasks. Existing work primarily focuses on one human sharing autonomy with a single robot.…
The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…
Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks…
A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can…
Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…