mlsanityData to 7 Oct 2026

2D-OOB: Attributing Data Contribution Through Joint Valuation Framework

arXiv 2408.03572 ↗First posted 7 Aug 2024cs.LG cs.AIcited by 4

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

Data valuation has emerged as a powerful framework for quantifying each datum's contribution to the training of a machine learning model. However, it is crucial to recognize that the quality of cells within a single data point can vary greatly in practice. For example, even in the case of an abnormal data point, not all cells are necessarily noisy. The single scalar score assigned by existing data valuation methods blurs the distinction between noisy and clean cells of a data point, making it challenging to interpret the data values. In this paper, we propose 2D-OOB, an out-of-bag estimation framework for jointly determining helpful (or detrimental) samples as well as the particular cells that drive them. Our comprehensive experiments demonstrate that 2D-OOB achieves state-of-the-art performance across multiple use cases while being exponentially faster. Specifically, 2D-OOB shows promising results in detecting and rectifying fine-grained outliers at the cell level, and localizing backdoor triggers in data poisoning attacks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 37 of its 54 references that are in the map. First posted on arXiv 7 Aug 2024.

Builds on

37 of 54 references.

References · 37

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  5. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  8. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  9. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
  10. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  11. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  12. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
25 more
  1. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 279
  2. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  3. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  4. 2021Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learningcited by 162
  5. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
  6. 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 147
  7. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  8. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 128
  9. 2019Data Valuation using Reinforcement Learningcited by 115
  10. 2023LAVA: Data Valuation without Pre-Specified Learning Algorithmscited by 69
  11. 2019OpenML-Python: an extensible Python API for OpenMLcited by 62
  12. 2023OpenDataVal: a Unified Benchmark for Data Valuationcited by 55
  13. 2020Efficient computation and analysis of distributional Shapley valuescited by 38
  14. 2023Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Valuecited by 38
  15. 2022WeightedSHAP: analyzing and improving Shapley based feature attributionscited by 36
  16. 2024Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMscited by 32
  17. 2020TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoorscited by 30
  18. 2024Rethinking Data Shapley for Data Selection Tasks: Misleads and Meritscited by 29
  19. 2024Efficient Data Shapley for Weighted Nearest Neighbor Algorithmscited by 18
  20. 2024Incentives in Private Collaborative Machine Learningcited by 10
  21. 2023Data Acquisition: A New Frontier in Data-centric AIcited by 9
  22. 2016Detecting deviating data cellscited by 8
  23. 20232D-Shapley: A Framework for Fragmented Data Valuationcited by 7
  24. 2023Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithmcited by 5
  25. 2021Robust Variable Selection under Cellwise Contaminationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2024LossVal: Efficient Data Valuation for Neural Networkscited by 1
  2. 2025KAIROS: Scalable Model-Agnostic Data Valuationcited by 1
  3. 2025Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuningcited by 0
  4. 2026On the Fragility of Data Attribution When Learning Is Distributedcited by 0