相关论文: DRIP: Defending Prompt Injection via Token-wise Re…

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security threat. By injecting malicious instructions into the data that…

Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications, which perform text-based tasks by utilizing their advanced language understanding capabilities. However, as LLMs have improved, so have the attacks…

When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker…

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious…

Recently, the advances in vision-language models, including contrastive pretraining and instruction tuning, have greatly pushed the frontier of multimodal AI. However, owing to the large-scale and hence expensive pretraining, the efficiency…

Large language models (LLMs) are becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advanced language understanding. To accomplish these tasks, the LLM…

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…

As LLM agents transition from digital assistants to physical controllers in autonomous systems and robotics, they face an escalating threat from indirect prompt injection. By embedding adversarial instructions into the results of tool…

We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to change how it…

Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities. By interacting with external environments through predefined tools, these agents can carry out complex user…

Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them together into a single stream of text. However, the LLM is…

Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, adapting LLMs to effectively handle structural data, such as knowledge graphs or web…

Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following, becoming increasingly crucial across various applications. However, this capability brings with it the risk of prompt injection attacks, where…

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…