相关论文: Ignore Previous Prompt: Attack Techniques For Lang…

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…

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…

Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public. However, the increasing concerns regarding the misuse of LLMs, such as plagiarism and spamming, have led to…

Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs…

Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new…

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

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…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

System prompts are widely used to guide the outputs of large language models (LLMs). These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries…

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,…

Large language models (LLMs) have succeeded significantly in various applications but remain susceptible to adversarial jailbreaks that void their safety guardrails. Previous attempts to exploit these vulnerabilities often rely on high-cost…

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety…

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…

The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness to prompts. In response to this vital need, we introduce PromptRobust, a robustness…

Large language models (LLMs) are renowned for their exceptional capabilities, and applying to a wide range of applications. However, this widespread use brings significant vulnerabilities. Also, it is well observed that there are huge gap…

The text generated by large language models is commonly controlled by prompting, where a prompt prepended to a user's query guides the model's output. The prompts used by companies to guide their models are often treated as secrets, to be…

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection, where malicious commands embedded in untrusted data…