mlsanityData to 7 Oct 2026

Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?

arXiv 2409.03741 ↗First posted 5 Sep 2024cs.CR cs.LGcited by 5

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

Machine learning has revolutionized numerous domains, playing a crucial role in driving advancements and enabling data-centric processes. The significance of data in training models and shaping their performance cannot be overstated. Recent research has highlighted the heterogeneous impact of individual data samples, particularly the presence of valuable data that significantly contributes to the utility and effectiveness of machine learning models. However, a critical question remains unanswered: are these valuable data samples more vulnerable to machine learning attacks? In this work, we investigate the relationship between data importance and machine learning attacks by analyzing five distinct attack types. Our findings reveal notable insights. For example, we observe that high importance data samples exhibit increased vulnerability in certain attacks, such as membership inference and model stealing. By analyzing the linkage between membership inference vulnerability and data importance, we demonstrate that sample characteristics can be integrated into membership metrics by introducing sample-specific criteria, therefore enhancing the membership inference performance. These findings emphasize the urgent need for innovative defense mechanisms that strike a balance between maximizing utility and safeguarding valuable data against potential exploitation.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 65 of its 80 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

65 of 80 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Membership Inference Attacks Against In-Context Learning2 Sep
  2. 2023Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models30 Oct
  3. 2023Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning17 Oct
  4. 2022Membership Inference Attacks by Exploiting Loss Trajectory31 Aug
  5. 2021Membership Inference Attacks From First Principles7 Dec
  6. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  7. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models4 Feb

Other references · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  10. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  11. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
  12. 2016Stealing Machine Learning Models via Prediction APIscited by 602
38 more
  1. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  2. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  3. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  4. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  5. 2020Label-Only Membership Inference Attackscited by 371
  6. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 338
  7. 2020Input-Aware Dynamic Backdoor Attackcited by 304
  8. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  9. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  10. 2023TRAK: Attributing Model Behavior at Scalecited by 273
  11. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  12. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 237
  13. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 213
  14. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 208
  15. 2020Information Leakage in Embedding Modelscited by 199
  16. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  17. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 188
  18. 2020Blind Backdoors in Deep Learning Modelscited by 174
  19. 2021Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learningcited by 162
  20. 2020Membership Leakage in Label-Only Exposurescited by 156
  21. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 155
  22. 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 147
  23. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 147
  24. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  25. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  26. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
  27. 2022The Privacy Onion Effect: Memorization is Relativecited by 128
  28. 2022BackdoorBench: A Comprehensive Benchmark of Backdoor Learningcited by 124
  29. 2020Data-Free Model Extractioncited by 121
  30. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
  31. 2020MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimationcited by 99
  32. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 94
  33. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  34. 2018A Marketplace for Data: An Algorithmic Solutioncited by 75
  35. 2022Variational Model Inversion Attackscited by 75
  36. 2019Overlearning Reveals Sensitive Attributescited by 74
  37. 2020Cryptanalytic Extraction of Neural Network Modelscited by 65
  38. 2020Knowledge-Enriched Distributional Model Inversion Attackscited by 65

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2024Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruningcited by 5
  2. 2025SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmarkcited by 5
  3. 2025CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakagecited by 3
  4. 2025AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agentscited by 2
  5. 2026No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerabilitycited by 0