相关论文: Detecting Verbatim LLM Copy-Paste in Homework

The integrity of peer review is fundamental to scientific progress, but the rise of large language models (LLMs) has introduced concerns that some reviewers may rely on these tools to generate reviews rather than writing them independently.…

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…

Watermarking is a technique that involves embedding nearly unnoticeable statistical signals within generated content to help trace its source. This work focuses on a scenario where an untrusted third-party user sends prompts to a trusted…

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…

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

As Large Language Models (LLMs) become increasingly sophisticated, they raise significant security concerns, including the creation of fake news and academic misuse. Most detectors for identifying model-generated text are limited by their…

As large language models (LLMs) become increasingly commonplace, concern about distinguishing between human and AI text increases as well. The growing power of these models is of particular concern to teachers, who may worry that students…

Large Language Models (LLMs) like ChatGPT are now widely used in writing and reviewing scientific papers. While this trend accelerates publication growth and reduces human workload, it also introduces serious risks. Papers written or…

Hidden LLM prompts have appeared in online documents with increasing frequency. Their goal is to trigger indirect prompt injection attacks while remaining undetected from human oversight, to manipulate LLM-powered automated document…

Large language models (LLMs) have witnessed a meteoric rise in popularity among the general public users over the past few months, facilitating diverse downstream tasks with human-level accuracy and proficiency. Prompts play an essential…

Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…

The potential for large language models (LLMs) to hide messages within plain text (steganography) poses a challenge to detection and thwarting of unaligned AI agents, and undermines faithfulness of LLMs reasoning. We explore the…

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…

We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably…

Large Language Models (LLMs) have demonstrated remarkable capabilities, but their training requires extensive data and computational resources, rendering them valuable digital assets. Therefore, it is essential to watermark LLMs to protect…

Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…

Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to…

Large language models (LLMs) trained purely on text ostensibly lack any direct perceptual experience, yet their internal representations are implicitly shaped by multimodal regularities encoded in language. We test the hypothesis that…