在线社交网络文本内容对抗技术

With prosperous development of social network and intensive research on natural language processing technology, adversarial technology of text content on online social networks becomes an emerging research direction in the field of artificial intelligence and cyberspace security. Adversarial technology of text content on online social networks refers to that in social network environment where there exists numerous users, huge amount of text contents, uneven quality of texts, ambiguous credibility of information, people employ the latest artificial intelligence methods to accomplish specific tasks such as discovery of machine-generated text, coherent and controllable text generation and adversarial content delivery for specific topics and targeted groups in online social networks automatically and precisely to filter the content in online social networks based on analysis of generation strategies, appropriate representation pattern of aimed groups, which could realize the detection and countermeasures of social platform abnormal information attack, increase the information credibility in social network, improve the quality of daily news received by social network users, enhance public trust on social media and protect cyberspace from information bombing and misleading information by reliable and economic means. Although online social network adversarial technology is a new concept with few related work, existing machine learning methods can be applied to this field by applying advanced technologies such as feature extraction, document parsing, encoding and reconstruction of text content, objective optimization on large scale social network text content dataset to solve the practical problem and clear the Internet environment. Besides, during the adversarial process of text content on online social networks, the strategies of the opposing parties can be used as feedback information to each other, so that the adversarial model is continuously updated and optimized, and finally the goal of perfecting the model is achieved. Based on the adversarial idea of attack and protection, this paper mainly describes the online social network adversarial technology from text content generation and machine-generated text content detection, respectively. Firstly, this paper introduces some basic knowledge about deep learning which is related to the online social network adversarial technology, including basic deep learning networks, pre-trained models and advanced deep learning networks. For generated social network content detection methods, this paper introduces it from different perspectives in detail, including zero-shot learning based models, machine feature based models, pre-trained language model based models, human-computer collaboration based models, and energy based models. For the convenience of choosing appropriate method to practice text content detection method in different scenes for readers, this paper makes comparison among different detection models in terms of applicable scenes, advantages and disadvantages. For social network text auto-generation methods, this paper summarizes four aspects of work, including text generation models based on adversarial generation networks, controllable text generation models, long text generation, and generated text quality evaluation. Besides, to help readers put the models into practice, verify the validity of the model and improve the shortcoming and performance of model with ease, this paper systematically summarizes the relevant datasets. Finally, this paper summarizes the important research directions and challenges of online social network adversarial technology in the future.