mlsanityData to 14 Oct 2026

On the Trade-Off Between Transparency and Security in Adversarial Machine Learning

arXiv 2511.11842 ↗First posted 14 Nov 2025cs.LG cs.CR cs.GTcited by 0

Not on the map. Why?

Abstract (arXiv)

Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In transferable adversarial example attacks, attackers maliciously perturb their inputs using surrogate models to fool a defender's target model. These models can be defended or undefended, with both players having to decide which to use. Using a large-scale empirical evaluation of nine attacks across 181 models, we find that attackers are more successful when they match the defender's decision; hence, obscurity could be beneficial to the defender. With game theory, we analyze this trade-off between transparency and security by modeling this problem as both a Nash game and a Stackelberg game, and comparing the expected outcomes. Our analysis confirms that only knowing whether a defender's model is defended or not can sometimes be enough to damage its security. This result serves as an indicator of the general trade-off between transparency and security, suggesting that transparency in AI systems can be at odds with security. Beyond adversarial machine learning, our work illustrates how game-theoretic reasoning can uncover conflicts between transparency and security.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 49 references that are in the map. First posted on arXiv 14 Nov 2025.

Builds on

23 of 49 references.

References · 23

  1. 2016Adversarial examples in the physical worldcited by 1,769
  2. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  3. 2016Adversarial Machine Learning at Scalecited by 936
  4. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  5. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  6. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  7. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  8. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  9. 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 156
  10. 2025Trading Inference-Time Compute for Adversarial Robustnesscited by 61
  11. 2023Boosting Adversarial Transferability by Achieving Flat Local Maximacited by 48
  12. 2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
11 more
  1. 2022LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinitycited by 39
  2. 2020Adversarial Example Gamescited by 34
  3. 2023Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabilitycited by 32
  4. 2017A Game-Theoretic Taxonomy and Survey of Defensive Deception for Cybersecurity and Privacycited by 22
  5. 2017Cascade Adversarial Machine Learning Regularized with a Unified Embeddingcited by 13
  6. 2019A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Taskscited by 12
  7. 2020Advocating for Multiple Defense Strategies against Adversarial Examplescited by 11
  8. 2022Game Theoretic Mixed Experts for Combinational Adversarial Machine Learningcited by 6
  9. 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairlycited by 6
  10. 2022A Survey of Decision Making in Adversarial Gamescited by 3
  11. 2024RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defensescited by 2

Built on by

Not cited yet.