KAWASAKI, Japan, Oct 29, 2020 - (JCN Newswire) - Fujitsu Laboratories Ltd. today announced the development of a technology to make AI models more robust against deception attacks. The technology protects against attempts to use forged attack data to trick AI models into making a deliberate misjudgment when AI is used for sequential data consisting of multiple elements. Figure 1: simple process of generating simulated data attackFigure 2: image of automatic generation of simulated attack dataFigure 3 image of ensemble adversarial training techniquesFigure 4: evaluation of the newly developed technologyWith the use of AI technologies progressing in various fields in recent years, the risk of attacks that intentionally interfere with AI's ability to make correct judgments represents a source of growing concern. Many suitable conventional security resistance enhancement technologies exist for media data like images and sound. Their application to sequential data such as communication logs and service usage history remains insufficient, however, because of the challenges posed by preparing simulated attack data and the loss of accuracy. To overcome these challenges, Fujitsu has develope...