Backdoor attacks and countermeasures on deep learning: A comprehensive review
This work provides the community with a timely comprehensive review of backdoor attacks
and countermeasures on deep learning. According to the attacker's capability and affected …
and countermeasures on deep learning. According to the attacker's capability and affected …
I know what you trained last summer: A survey on stealing machine learning models and defences
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 …
even the most complex Machine Learning models available for clients via, eg, a pay-per …
The false promise of imitating proprietary llms
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 …
outputs from a stronger model, such as a proprietary system like ChatGPT (eg, Alpaca, Self …
Cater: Intellectual property protection on text generation apis via conditional watermarks
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 …
attacks, causing IP violations. In order to protect the IP of text generation APIs, recent work …
A survey on ChatGPT: AI-generated contents, challenges, and solutions
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 …
generated content (AIGC) has garnered increasing attention and is leading a paradigm shift …
M4: Multi-generator, multi-domain, and multi-lingual black-box machine-generated text detection
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 …
responses to a wide variety of user queries. However, this has also raised concerns about …
A recipe for watermarking diffusion models
Recently, diffusion models (DMs) have demonstrated their advantageous potential for
generative tasks. Widespread interest exists in incorporating DMs into downstream …
generative tasks. Widespread interest exists in incorporating DMs into downstream …
Protecting intellectual property of language generation apis with lexical watermark
Nowadays, due to the breakthrough in natural language generation (NLG), including
machine translation, document summarization, image captioning, etc NLG models have …
machine translation, document summarization, image captioning, etc NLG models have …
A survey of deep neural network watermarking techniques
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 …
Networks (DNNs) is a pressing need pushed by the high costs required to train such …
Thieves on sesame street! model extraction of bert-based apis
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 …
adversary with only query access to a victim model attempts to reconstruct a local copy of …