all AI news
A Reinforcement Learning-based Offensive semantics Censorship System for Chatbots. (arXiv:2207.10569v1 [cs.CL])
cs.CL updates on arXiv.org arxiv.org
The rapid development of artificial intelligence (AI) technology has enabled
large-scale AI applications to land in the market and practice. However, while
AI technology has brought many conveniences to people in the productization
process, it has also exposed many security issues. Especially, attacks against
online learning vulnerabilities of chatbots occur frequently. Therefore, this
paper proposes a semantics censorship chatbot system based on reinforcement
learning, which is mainly composed of two parts: the Offensive semantics
censorship model and the semantics purification …
arxiv censorship chatbots learning reinforcement reinforcement learning semantics