On Codomain Separability and Label Inference from (Noisy) Loss Functions

• URL: http://arxiv.org/abs/2107.03022v1
• Date: Wed, 7 Jul 2021 05:29:53 GMT
• Title: On Codomain Separability and Label Inference from (Noisy) Loss Functions
• Authors: Abhinav Aggarwal, Shiva Prasad Kasiviswanathan, Zekun Xu, Oluwaseyi Feyisetan, Nathanael Teissier
• Abstract summary: We introduce the notion of codomain separability to study the necessary and sufficient conditions under which label inference is possible from any (noisy) loss function values. We show that for many commonly used loss functions, including multiclass cross-entropy with common activation functions and some Bregman divergence-based losses, it is possible to design label inference attacks for arbitrary noise levels.
• Score: 11.780563744330038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning classifiers rely on loss functions for performance evaluation, often on a private (hidden) dataset. Label inference was recently introduced as the problem of reconstructing the ground truth labels of this private dataset from just the (possibly perturbed) loss function values evaluated at chosen prediction vectors, without any other access to the hidden dataset. Existing results have demonstrated this inference is possible on specific loss functions like the cross-entropy loss. In this paper, we introduce the notion of codomain separability to formally study the necessary and sufficient conditions under which label inference is possible from any (noisy) loss function values. Using this notion, we show that for many commonly used loss functions, including multiclass cross-entropy with common activation functions and some Bregman divergence-based losses, it is possible to design label inference attacks for arbitrary noise levels. We demonstrate that these attacks can also be carried out through actual neural network models, and argue, both formally and empirically, the role of finite precision arithmetic in this setting.

Related papers

• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• Robust Loss Functions for Training Decision Trees with Noisy Labels [4.795403008763752]
  We consider training decision trees using noisily labeled data, focusing on loss functions that can lead to robust learning algorithms. First, we offer novel theoretical insights on the robustness of many existing loss functions in the context of decision tree learning. Second, we introduce a framework for constructing robust loss functions, called distribution losses.
  arXiv  Detail & Related papers  (2023-12-20T11:27:46Z)
• Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention [30.389055604165222]
  We introduce new families of surrogate losses for the abstention loss function. We prove strong non-asymptotic and hypothesis set-specific consistency guarantees for these surrogate losses. Our results show that the relative performance of the state-of-the-art score-based surrogate losses can vary across datasets.
  arXiv  Detail & Related papers  (2023-10-23T10:13:35Z)
• Noise-Robust Loss Functions: Enhancing Bounded Losses for Large-Scale Noisy Data Learning [0.0]
  Large annotated datasets inevitably contain noisy labels, which poses a major challenge for training deep neural networks as they easily memorize the labels. Noise-robust loss functions have emerged as a notable strategy to counteract this issue, but it remains challenging to create a robust loss function which is not susceptible to underfitting. We propose a novel method denoted as logit bias, which adds a real number $epsilon$ to the logit at the position of the correct class.
  arXiv  Detail & Related papers  (2023-06-08T18:38:55Z)
• The Fisher-Rao Loss for Learning under Label Noise [9.238700679836855]
  We study the Fisher-Rao loss function, which emerges from the Fisher-Rao distance in the statistical manifold of discrete distributions. We derive an upper bound for the performance degradation in the presence of label noise, and analyse the learning speed of this loss.
  arXiv  Detail & Related papers  (2022-10-28T20:50:10Z)
• The Group Loss++: A deeper look into group loss for deep metric learning [65.19665861268574]
  Group Loss is a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group. We show state-of-the-art results on clustering and image retrieval on four datasets, and present competitive results on two person re-identification datasets.
  arXiv  Detail & Related papers  (2022-04-04T14:09:58Z)
• Learning with Noisy Labels via Sparse Regularization [76.31104997491695]
  Learning with noisy labels is an important task for training accurate deep neural networks. Some commonly-used loss functions, such as Cross Entropy (CE), suffer from severe overfitting to noisy labels. We introduce the sparse regularization strategy to approximate the one-hot constraint.
  arXiv  Detail & Related papers  (2021-07-31T09:40:23Z)
• Memorization in Deep Neural Networks: Does the Loss Function matter? [1.71982924656402]
  We show that a symmetric loss function, as opposed to either cross-entropy or squared error loss, results in significant improvement in the ability of the network to resist such overfitting. Our results clearly bring out the role loss functions alone can play in this phenomenon of memorization.
  arXiv  Detail & Related papers  (2021-07-21T09:08:51Z)
• Searching for Robustness: Loss Learning for Noisy Classification Tasks [81.70914107917551]
  We parameterize a flexible family of loss functions using Taylors and apply evolutionary strategies to search for noise-robust losses in this space. The resulting white-box loss provides a simple and fast "plug-and-play" module that enables effective noise-robust learning in diverse downstream tasks.
  arXiv  Detail & Related papers  (2021-02-27T15:27:22Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)
• An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay [72.23433407017558]
  We show that any loss function evaluated with non-uniformly sampled data can be transformed into another uniformly sampled loss function. Surprisingly, we find in some environments PER can be replaced entirely by this new loss function without impact to empirical performance.
  arXiv  Detail & Related papers  (2020-07-12T17:45:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.