Proceedings of the AAAI Conference on Artificial Intelligence · 2022 · 52 citations · 46 references
ComputingCloud ComputingComputer ScienceCloud SecurityIntellectual PropertyNatural Language ProcessingApi SecurityLanguage ModelingMachine TranslationNatural Language GenerationText GenerationText SummarizationAutomated Text GenerationDocument SummarizationForensic WatermarkingImage CaptioningLanguage GenerationText WatermarksWatermark DetectionWatermarking
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have been encapsulated in cloud APIs to serve over half a billion people worldwide and process over one hundred billion word generations per day. Thus, NLG APIs have already become essential profitable services in many commercial companies. Due to the substantial financial and intellectual investments, service providers adopt a pay-as-you-use policy to promote sustainable market growth. However, recent works have shown that cloud platforms suffer from financial losses imposed by model extraction attacks, which aim to imitate the functionality and utility of the victim services, thus violating the intellectual property (IP) of cloud APIs. This work targets at protecting IP of NLG APIs by identifying the attackers who have utilized watermarked responses from the victim NLG APIs. However, most existing watermarking techniques are not directly amenable for IP protection of NLG APIs. To bridge this gap, we first present a novel watermarking method for text generation APIs by conducting lexical modification to the original outputs. Compared with the competitive baselines, our watermark approach achieves better identifiable performance in terms of p-value, with fewer semantic losses. In addition, our watermarks are more understandable and intuitive to humans than the baselines. Finally, the empirical studies show our approach is also applicable to queries from different domains, and is effective on the attacker trained on a mixture of the corpus which includes less than 10% watermarked samples.
46
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
Distilling the Knowledge in a Neural Network
Geoffrey E. Hinton, Oriol Vinyals · arXiv (Cornell University) · 2015 · 14K citations · Full text
ROUGE: A Package for Automatic Evaluation of Summaries
Chin-Yew Lin · 2004 · 8.3K citations