An Anti-Poisoning Attack Method for Distributed AI System

In distributed AI system, the models trained on data from potentially unreliable sources can be attacked by manipulating the training data distribution by inserting carefully crafted samples into the training set, which is known as Data Poisoning. Poisoning will to change the model behavior and reduce model performance. This paper proposes an algorithm that gives an improvement of both efficiency and security for data poisoning in a distributed AI system. The past methods of active defense often have a large number of invalid checks, which slows down the operation efficiency of the whole system. While passive defense also has problems of missing data and slow detection of error source. The proposed algorithm establishes the suspect hypothesis level to test and extend the verification of data packets and estimates the risk of terminal data. It can enhance the health degree of a distributed AI system by preventing the occurrence of poisoning attack and ensuring the efficiency and safety of the system operation.

情绪识别技术的问题、风险与规治

情绪识别技术是人工智能领域的一项新技术,既能提升人的情绪识别能力也能增强机器的智能水平,进而可能带来新的人机交互革命。情绪识别技术有其特殊的理论基础和本质特征,它们必然地引发了相应的问题和风险。该技术的主要风险是:低效易错的情绪识别设备将给人带来生理和心理上的双重伤害,恶化人机关系;高效准确的情绪识别设备可能会侵犯个人隐私,并带来社会公平正义等诸多问题;越界使用导致了不可控风险。为了尽可能减少相应风险,需要针对该技术的理论基础与本质特点进行规范和治理。一个金字塔式综合规治方案是:(1)在顶层提炼情绪识别技术的基本伦理原则。(2)在中层进行分级治理。审视科学证据是否支持情绪识别技术完成特定领域的任务,考察每一类应用普遍化的过程合理性和伦理后果,最终划定风险等级以便精细化治理。(3)在底层提出情绪评估强度概念。根据不同的风险等级,为机器定制不同的情绪评估强度。