Machine-Learning-as-a-Service (MLaaS) has become a widespread paradigm, making even the most complex Machine Learning models available for clients via, eg, a pay-per …
An emerging method to cheaply improve a weaker language model is to finetune it on outputs from a stronger model, such as a proprietary system like ChatGPT (eg, Alpaca, Self …
X He, Q Xu, Y Zeng, L Lyu, F Wu… - Advances in Neural …, 2022 - proceedings.neurips.cc
Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, recent work …
Y Wang, Y Pan, M Yan, Z Su… - IEEE Open Journal of the …, 2023 - ieeexplore.ieee.org
With the widespread use of large artificial intelligence (AI) models such as ChatGPT, AI- generated content (AIGC) has garnered increasing attention and is leading a paradigm shift …
Y Wang, J Mansurov, P Ivanov, J Su… - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models (LLMs) have demonstrated remarkable capability to generate fluent responses to a wide variety of user queries. However, this has also raised concerns about …
Recently, diffusion models (DMs) have demonstrated their advantageous potential for generative tasks. Widespread interest exists in incorporating DMs into downstream …
X He, Q Xu, L Lyu, F Wu, C Wang - … of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have …
Abstract Protecting the Intellectual Property Rights (IPR) associated to Deep Neural Networks (DNNs) is a pressing need pushed by the high costs required to train such …
We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of …