arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.12151cs.LGcs.AI
收藏

基于对抗攻击造成的损害风险的模型选择

Selecting Models based on the Risk of Damage Caused by Adversarial Attacks

neurocat(neurocat公司)

Jona Klemenc, Holger Trittenbach

摘要:

监管、法律责任和社会问题对人工智能在安全和安全关键型应用中的采用提出了挑战。其中一个关键问题是,对手可以通过操纵模型预测而不被发现来造成伤害。因此,监管要求对对手造成损害的风险进行评估。然而,没有方法将这种高层次的需求转化为量化损害风险的可操作指标。在这篇文章中,我们提出了一种方法来建模和统计估计的损害概率所产生的对抗攻击。我们表明,我们提出的估计是统计一致和无偏的。在实验中,我们证明了我们的方法的估计结果有一个明确的和可操作的解释,并优于传统的指标。然后,我们将展示运营商如何使用估计结果来可靠地选择风险最低的模型。

英文摘要:

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.

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。

↑