The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

The integration of Large Language Models (LLMs) and Edge Intelligence (EI) introduces a
groundbreaking paradigm for intelligent edge devices. With their capacity for human-like …

Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow
adversaries to overwrite a model's original instructions with their own malicious prompts. In …

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions,
and interact with external content (eg, emails or websites). However, external content …

Large Language Models (LLMs) have achieved remarkable success across diverse tasks,
yet they remain vulnerable to adversarial attacks, notably the well-documented\textit …

Generalist web agents have evolved rapidly and demonstrated remarkable potential.
However, there are unprecedented safety risks associated with these them, which are nearly …

Vision-language models (VLMs) are essential for contextual understanding of both visual
and textual information. However, their vulnerability to adversarially manipulated inputs …

Large Language Models (LLMs) have gained widespread use in various applications due to
their powerful capability to generate human-like text. However, prompt injection attacks …

AI agents aim to solve complex tasks by combining text-based reasoning with external tool
calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned …

Large Language Models (LLMs) are increasingly used in applications where the model
selects from competing third-party content, such as in LLM-powered search engines or …