欺骗性AI声明的创建与检测
Deceptive AI Explanations: Creation and Detection
摘要:
人工智能(AI)带来了巨大的机遇,但也可能带来重大风险。自动生成的决策解释可以提高透明度并促进信任,特别是对于基于人工智能模型自动预测的系统。然而,鉴于,例如,经济激励创造不诚实的人工智能,我们在多大程度上可以相信解释?为了解决这个问题,我们的工作研究了人工智能模型(即,深度学习和现有的提高人工智能决策透明度的工具)可以用于创建和检测欺骗性解释。作为一个实证评估,我们专注于文本分类,并改变GradCAM,一个完善的解释技术,在神经网络产生的解释。然后,我们评估了欺骗性解释对用户的影响,在一个有200名参与者的实验。我们的发现证实了欺骗性的解释确实可以愚弄人类。然而,人们可以部署机器学习(ML)方法来检测看似轻微的欺骗尝试,在给定足够的领域知识的情况下,准确率超过80%。在没有领域知识的情况下,人们仍然可以以无监督的方式推断解释中的不一致性,给出了仔细审查的预测模型的基本知识。
英文摘要:
Artificial intelligence (AI) comes with great opportunities but can also pose significant risks. Automatically generated explanations for decisions can increase transparency and foster trust, especially for systems based on automated predictions by AI models. However, given, e.g., economic incentives to create dishonest AI, to what extent can we trust explanations? To address this issue, our work investigates how AI models (i.e., deep learning, and existing instruments to increase transparency regarding AI decisions) can be used to create and detect deceptive explanations. As an empirical evaluation, we focus on text classification and alter the explanations generated by GradCAM, a well-established explanation technique in neural networks. Then, we evaluate the effect of deceptive explanations on users in an experiment with 200 participants. Our findings confirm that deceptive explanations can indeed fool humans. However, one can deploy machine learning (ML) methods to detect seemingly minor deception attempts with accuracy exceeding 80% given sufficient domain knowledge. Without domain knowledge, one can still infer inconsistencies in the explanations in an unsupervised manner, given basic knowledge of the predictive model under scrutiny.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。