Related papers: Watermarking Makes Language Models Radioactive

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.…

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

We want to detect whether a particular image dataset has been used to train a model. We propose a new technique, \emph{radioactive data}, that makes imperceptible changes to this dataset such that any model trained on it will bear an…

The increasing availability of large language models (LLMs) has raised concerns about their potential misuse in online learning. While tools for detecting LLM-generated text exist and are widely used by researchers and educators, their…

As Large Language Models (LLMs) become increasingly prevalent, their generated outputs are proliferating across the web, risking a future where machine-generated content dilutes human-authored text. Since online data is the primary resource…

Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from some users. Existing utility-centric unlearning metrics…

Large language models (LLMs) are increasingly integrated into academic workflows, with many conferences and journals permitting their use for tasks such as language refinement and literature summarization. However, their use in peer review…

In response to the growing popularity of Machine Learning (ML) techniques to solve problems in various industries, various malicious groups have started to target such techniques in their attack plan. However, as ML models are constantly…

Since the proliferation of LLMs, there have been concerns about their misuse for harmful content creation and spreading. Recent studies justify such fears, providing evidence of LLM vulnerabilities and high potential of their misuse. Humans…

In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the…

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…

Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution,…

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

Text watermarking plays a crucial role in ensuring the traceability and accountability of large language model (LLM) outputs and mitigating misuse. While promising, most existing methods assume perfect pseudorandomness. In practice,…

Advances in generative models have made it possible for AI-generated text, code, and images to mirror human-generated content in many applications. Watermarking, a technique that aims to embed information in the output of a model to verify…

While watermarks for closed LLMs have matured and have been included in large-scale deployments, these methods are not applicable to open-source models, which allow users full control over the decoding process. This setting is understudied…

While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. In this paper, we provide evidence that the…

LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark…

Automated disinformation generation is often listed as an important risk associated with large language models (LLMs). The theoretical ability to flood the information space with disinformation content might have dramatic consequences for…