Abstract
Regulation, legal liabilities, and societal concerns challenge the adoption of AI in safety and security-critical applications. One of the key concerns is that adversaries can cause harm by manipulating model predictions without being detected. Regulation hence demands an assessment of the risk of damage caused by adversaries. Yet, there is no method to translate this high-level demand into actionable metrics that quantify the risk of damage. In this article, we propose a method to model and statistically estimate the probability of damage arising from adversarial attacks. We show that our proposed estimator is statistically consistent and unbiased. In experiments, we demonstrate that the estimation results of our method have a clear and actionable interpretation and outperform conventional metrics. We then show how operators can use the estimation results to reliably select the model with the lowest risk.
Abstract (translated)
监管、法律责任和社会关切挑战在安全和安保关键应用中采用人工智能的问题。其中一个关键关切是敌对势力可以通过操纵模型预测而造成损害的可能性。因此,规定要求评估敌对势力所造成损害的风险。然而,没有方法可以将这一高层次要求转化为可操作的指标,以量化损害的风险。在本文中,我们提出一种方法来建模并统计估计由对抗攻击引起的损害概率。我们表明,我们提出的估计器具有统计一致性和无偏差性。在实验中,我们证明,我们的方法的估计结果具有清晰和可操作的解释,并比传统指标表现更好。随后,我们展示了 operators 如何使用估计结果来可靠地选择模型,以最小化风险。
URL
https://arxiv.org/abs/2301.12151
