Related papers: Fingerprinting LLMs via Prompt Injection

Watermarking the outputs of large language models (LLMs) is critical for provenance tracing, content regulation, and model accountability. Existing approaches often rely on access to model internals or are constrained by static rules and…

This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-content attribution. Large language models (LLMs) require substantial investments in data,…

System prompts that include detailed instructions to describe the task performed by the underlying LLM can easily transform foundation models into tools and services with minimal overhead. They are often considered intellectual property,…

Large language models (LLMs) can perform recommendation tasks by taking prompts written in natural language as input. Compared to traditional methods such as collaborative filtering, LLM-based recommendation offers advantages in handling…

Fingerprinting large language models (LLMs) is essential for verifying model ownership, ensuring authenticity, and preventing misuse. Traditional fingerprinting methods often require significant computational overhead or white-box…

The broad capabilities and substantial resources required to train Large Language Models (LLMs) make them valuable intellectual property, yet they remain vulnerable to copyright infringement, such as unauthorized use and model theft. LLM…

Large language models (LLMs) face significant copyright and intellectual property challenges as the cost of training increases and model reuse becomes prevalent. While watermarking techniques have been proposed to protect model ownership,…

Large language models (LLMs) have been massively applied to many tasks, often surpassing state-of-the-art approaches. While their effectiveness in code generation has been extensively studied (e.g., AlphaCode), their potential for code…

The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…

Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted…

Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) has become increasingly crucial. As the standard paradigm for IP ownership verification, LLM fingerprinting thus plays a…

It has been shown that finetuned transformers and other supervised detectors effectively distinguish between human and machine-generated text in some situations arXiv:2305.13242, but we find that even simple classifiers on top of n-gram and…

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Large Language Models (LLMs) have achieved remarkable performance and received significant research interest. The enormous computational demands, however, hinder the local deployment on devices with limited resources. The current prevalent…

Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for establishing model…

Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the…

Despite providing superior performance, open-source large language models (LLMs) are vulnerable to abusive usage. To address this issue, recent works propose LLM fingerprinting methods to identify the specific source LLMs behind suspect…

Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize…

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…