Temperature Matters: Enhancing Watermark Robustness Against Paraphrasing Attacks
This work addresses the need for ethical AI text generation by improving watermarking techniques, though it appears incremental as it builds on prior methods.
The paper tackles the problem of detecting synthetic text from Large Language Models by proposing a new watermarking method, which shows enhanced robustness against paraphrasing attacks compared to a baseline approach.
In the present-day scenario, Large Language Models (LLMs) are establishing their presence as powerful instruments permeating various sectors of society. While their utility offers valuable support to individuals, there are multiple concerns over potential misuse. Consequently, some academic endeavors have sought to introduce watermarking techniques, characterized by the inclusion of markers within machine-generated text, to facilitate algorithmic identification. This research project is focused on the development of a novel methodology for the detection of synthetic text, with the overarching goal of ensuring the ethical application of LLMs in AI-driven text generation. The investigation commences with replicating findings from a previous baseline study, thereby underscoring its susceptibility to variations in the underlying generation model. Subsequently, we propose an innovative watermarking approach and subject it to rigorous evaluation, employing paraphrased generated text to asses its robustness. Experimental results highlight the robustness of our proposal compared to the~\cite{aarson} watermarking method.