设计最优测试策略，让作弊者无法扭曲真实结果。
Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers
- 用动态规划寻找最优再测方案，应对作弊干扰
- 即使存在作弊者，仍能准确恢复真实测试结果
- 适合考试防作弊、AI内容检测等安全敏感场景
在实际应用中，常需对对象或人员进行测试以评估其在特定指标下的表现。然而，测试结果不仅天然存在噪声，还可能被被测对象（测试者）的对抗行为污染。例如，不诚实的测试者可通过作弊手段扭曲结果。随着AI技术的发展，利用AI作弊导致的结果失真日益普遍且严重。本文提出一种最优测试策略，可在存在作弊者污染的情况下仍恢复所需的真实测试结果。该策略通过动态规划方法确定，对选定群体采用不同安全级别的再测措施，从而实现最优结果恢复。
原文摘要 · Abstract (English)
In applications, it is often required to test objects or people to determine their qualities in terms of certain metrics. However, besides being naturally noisy, the test results can be corrupted by adversarial behaviors of objects or people being tested (test takers). For example, dishonest test takers can cheat in the exams to distort the test results. With the development of AI technologies, such distortions driven by cheating using AI technologies are becoming more commonplace and severe. In this paper, we propose optimal testing strategies which can still recover needed test results even if there are cheaters polluting the results. The proposed testing strategies will optimally re-test selected group of test takers using different testing security measures. We determine the optimal testing strategies using a dynamic programming method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。