Related papers: Can We Trust Embodied Agents? Exploring Backdoor A…
In order to flexibly act in an everyday environment, a robotic agent needs a variety of cognitive capabilities that enable it to reason about plans and perform execution recovery. Large language models (LLMs) have been shown to demonstrate…
Recently, applications powered by Large Language Models (LLMs) have made significant strides in tackling complex tasks. By harnessing the advanced reasoning capabilities and extensive knowledge embedded in LLMs, these applications can…
Robotic manipulation policies are increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recently, inference-time attacks…
Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However,…
Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…
As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…
Large language models (LLMs), such as ChatGPT, have emerged with astonishing capabilities approaching artificial general intelligence. While providing convenience for various societal needs, LLMs have also lowered the cost of generating…
Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly…
The integration of Large Language Models (LLMs) like GPT-4o into robotic systems represents a significant advancement in embodied artificial intelligence. These models can process multi-modal prompts, enabling them to generate more…
Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing…
A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…
Language agents powered by large language models (LLMs) have seen exploding development. Their capability of using language as a vehicle for thought and communication lends an incredible level of flexibility and versatility. People have…
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…
We explore \textbf{C}ross-lingual \textbf{B}ackdoor \textbf{AT}tacks (X-BAT) in multilingual Large Language Models (mLLMs), revealing how backdoors inserted in one language can automatically transfer to others through shared embedding…
Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…
Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…
Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues,…
Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of…
Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…