Skip to content
DraconiticResearch
Search Sources API
186,123 studies31 sourcesUpdated 46 min ago
PreprintCC BY-NC-SA 4.0arXiv

Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers

  • Owen Cox
  • April Xu
  • Weiyu Xu
Open at sourcePDFDOICite

Abstract

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.

Related

  1. Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport
    Kim Jakwang, Kwon Dohyun
    arXivPreprintCC BY 4.0Full textProbabilityStatisticsarXiv
  2. GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial Testing
    Masahiro Kato
    arXivPreprintCC BY-NC-ND 4.0Full textStatisticsarXiv
  3. Robust dimension-free estimation of simple random tensors: optimal guarantees under heavy tails and adversarial contamination
    Roberto I. Oliveira, Zoraida F. Rico, Philip Thompson
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  4. Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning
    Alireza Abdollahpoorrostam, Ehsan Sharifian, Buse Şen +2
    arXivPreprintCC BY 4.0Full textOptimisation & controlStatisticsarXiv
  5. Nearly Minimax Optimal Regret for Adversarial Linear Bandits with Strong Corruptions
    Qiwei Di, Quanquan Gu
    arXivPreprintCC BY 4.0Full textStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{cox2026optimal,
  title = {{Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers}},
  author = {Owen Cox and April Xu and Weiyu Xu},
  howpublished = {arXiv},
  year = {2026},
  month = aug,
  doi = {10.48550/arxiv.2608.28362},
  eprint = {2608.28362},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.28362},
  note = {CC BY-NC-SA 4.0},
}
RIS
TY  - UNPB
TI  - Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers
AU  - Owen Cox
AU  - April Xu
AU  - Weiyu Xu
PY  - 2026
DA  - 2026/08/28
PB  - arXiv
DO  - 10.48550/arxiv.2608.28362
UR  - https://arxiv.org/abs/2608.28362
AB  - 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.
ER  -