Watermarking Text Generated by Black-Box Language Models
LLMs now exhibit human-like skills in various fields, leading to worries about misuse. Thus, detecting generated text is crucial. However, passive detection methods are stuck in domain specificity and limited adversarial robustness. To achieve reliable detection, a watermark-based method was proposed for white-box LLMs, allowing them to embed watermarks during text generation. The method involves randomly dividing the model vocabulary to obtain a special list and adjusting the probability distribution to promote the selection of words in the list. A detection algorithm aware of the list can identify the watermarked text. However, this method is not applicable in many real-world scenarios where only black-box language models are available. For instance, third-parties that develop API-based vertical applications cannot watermark text themselves because API providers only supply generated text and withhold probability distributions to shield their commercial interests. To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios. Specifically, we first define a binary encoding function to compute a random binary encoding corresponding to a word. The encodings computed for non-watermarked text conform to a Bernoulli distribution, wherein the probability of a word representing bit-1 being approximately 0.5. To inject a watermark, we alter the distribution by selectively replacing words representing bit-0 with context-based synonyms that represent bit-1. A statistical test is then used to identify the watermark. Experiments demonstrate the effectiveness of our method on both Chinese and English datasets. Furthermore, results under re-translation, polishing, word deletion, and synonym substitution attacks reveal that it is arduous to remove the watermark without compromising the original semantics.
Code (1)
Tasks
Adversarial RobustnessLanguage ModellingSpecificityText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Revisiting the Robustness of Watermarking to Paraphrasing Attacks
Amidst rising concerns about the internet being proliferated with content generated from language models (LMs), watermarking is seen as a principled way to certify whether text was generated from a model. Many recent wat…
Black-Box Detection of Language Model Watermarks
Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which …
Language ModelingLanguage ModellingmodelAudioMarkBench: Benchmarking Robustness of Audio Watermarking
The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embeddin…
Benchmarkingtext-to-speechText to SpeechYet Another Watermark for Large Language Models
Existing watermarking methods for large language models (LLMs) mainly embed watermark by adjusting the token sampling prediction or post-processing, lacking intrinsic coupling with LLMs, which may significantly reduce th…
AuthentiGPT: Detecting Machine-Generated Text via Black-Box Language Models Denoising
Large language models (LLMs) have opened up enormous opportunities while simultaneously posing ethical dilemmas. One of the major concerns is their ability to create text that closely mimics human writing, which can lead…
DenoisingLanguage ModelingLanguage Modelling