相关论文: Learning to Inject: Automated Prompt Injection via…

LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which…

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based…

LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to bypass safety guardrails and elicit harmful responses.…

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 by external tools hijacks the agent to execute…

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt…

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense -- falsely flagging benign inputs as…

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions…

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results…

Large Language Models (LLMs) are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial…

Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…

This paper introduces a novel self-consciousness defense mechanism for Large Language Models (LLMs) to combat prompt injection attacks. Unlike traditional approaches that rely on external classifiers, our method leverages the LLM's inherent…

Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt…

This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability in achieving high-quality annotation in various tasks, the…

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…