Visible to the public Data Poisoning Attack on Deep Neural Network and Some Defense Methods

TitleData Poisoning Attack on Deep Neural Network and Some Defense Methods
Publication TypeConference Paper
Year of Publication2020
AuthorsDang, Tran Khanh, Truong, Phat T. Tran, Tran, Pi To
Conference Name2020 International Conference on Advanced Computing and Applications (ACOMP)
KeywordsAdversarial Machine Learning, AI Poisoning, artificial intelligence, Deep Learning, Human Behavior, information technology, Neural networks, poisoning attack, pubcrawl, Resiliency, Scalability, secure learning, Security in Deep Learning, software engineering, Technological innovation
AbstractIn recent years, Artificial Intelligence has disruptively changed information technology and software engineering with a proliferation of technologies and applications based-on it. However, recent researches show that AI models in general and the most greatest invention since sliced bread - Deep Learning models in particular, are vulnerable to being hacked and can be misused for bad purposes. In this paper, we carry out a brief review of data poisoning attack - one of the two recently dangerous emerging attacks - and the state-of-the-art defense methods for this problem. Finally, we discuss current challenges and future developments.
Citation Keydang_data_2020