mlsanityData to 7 Oct 2026

SoK: Unintended Interactions among Machine Learning Defenses and Risks

arXiv 2312.04542 ↗First posted 7 Dec 2023cs.CR cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or decreased susceptibility to other risks. Existing research lacks an effective framework to recognize and explain these unintended interactions. We present such a framework, based on the conjecture that overfitting and memorization underlie unintended interactions. We survey existing literature on unintended interactions, accommodating them within our framework. We use our framework to conjecture on two previously unexplored interactions, and empirically validate our conjectures.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 173 of its 218 references that are in the map. First posted on arXiv 7 Dec 2023.

Builds on

173 of 218 references.

References · 173

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2020Extracting Training Data from Large Language Modelscited by 2,144
  8. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  9. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  10. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  11. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  12. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
38 more
  1. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  2. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  3. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  6. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  7. 2017A Closer Look at Memorization in Deep Networkscited by 936
  8. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
  9. 2018Robustness May Be at Odds with Accuracycited by 873
  10. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  11. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  12. 2023Extracting Training Data from Diffusion Modelscited by 723
  13. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  14. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  15. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  16. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  17. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  18. 2018A Reductions Approach to Fair Classificationcited by 585
  19. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 565
  20. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 547
  21. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  22. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  23. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  24. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  25. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 452
  26. 2017On Fairness and Calibrationcited by 406
  27. 2020Label-Only Membership Inference Attackscited by 371
  28. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  29. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  30. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  31. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  32. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  33. 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
  34. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  35. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  36. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 279
  37. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  38. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237

50 most cited of 173 All 173 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

  1. 2024Combining Machine Learning Defenses without Conflictscited by 2
  2. 2025AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agentscited by 2
  3. 2025Amulet: a Python Library for Assessing Interactions Among ML Defenses and Riskscited by 1
  4. 2026AI Security Research Should Better Incentivize Defense Researchcited by 0
  5. 2026SoK: Colluding Adversaries in Machine Learning Pipelinescited by 0
  6. 2026Model Stealing Through the Lens of Model Multiplicitycited by 0