相关论文: When AI Meets the Web: Prompt Injection Risks in T…

Large language models (LLMs) have shown incredible capabilities and transcended the natural language processing (NLP) community, with adoption throughout many services like healthcare, therapy, education, and customer service. Since users…

This paper comprehensively explores the ethical challenges arising from security threats to Large Language Models (LLMs). These intricate digital repositories are increasingly integrated into our daily lives, making them prime targets for…

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly…

With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse,…

While Large Language Models (LLMs) are rapidly integrating into daily life, research on their risks often remains lab-based and disconnected from the problems users encounter "in the wild." While recent HCI research has begun to explore…

Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…

Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions…

While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to prompt injection attacks: malicious third party prompts that subvert the intent of the system designer. To help researchers…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…

Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing…

Large Language Models (LLMs) are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs could introduce critical vulnerabilities in these systems. Here, we examine…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

ChatGPT and other large language models (LLMs) have proven useful in crowdsourcing tasks, where they can effectively annotate machine learning training data. However, this means that they also have the potential for misuse, specifically to…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…

Patients with schizophrenia often present with cognitive impairments that may hinder their ability to learn about their condition. These individuals could benefit greatly from education platforms that leverage the adaptability of Large…

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…