Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten

• URL: http://arxiv.org/abs/2508.07458v1
• Date: Sun, 10 Aug 2025 19:08:18 GMT
• Title: Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
• Authors: Wei Qian, Chenxu Zhao, Yangyi Li, Wenqian Ye, Mengdi Huai,
• Abstract summary: We propose a new class of malicious unlearning attacks against predictive uncertainties.<n>Our experiments show that our attacks are more effective in manipulating predictive uncertainties than traditional attacks.
• Score: 16.03102654663785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Currently, various uncertainty quantification methods have been proposed to provide certainty and probability estimates for deep learning models' label predictions. Meanwhile, with the growing demand for the right to be forgotten, machine unlearning has been extensively studied as a means to remove the impact of requested sensitive data from a pre-trained model without retraining the model from scratch. However, the vulnerabilities of such generated predictive uncertainties with regard to dedicated malicious unlearning attacks remain unexplored. To bridge this gap, for the first time, we propose a new class of malicious unlearning attacks against predictive uncertainties, where the adversary aims to cause the desired manipulations of specific predictive uncertainty results. We also design novel optimization frameworks for our attacks and conduct extensive experiments, including black-box scenarios. Notably, our extensive experiments show that our attacks are more effective in manipulating predictive uncertainties than traditional attacks that focus on label misclassifications, and existing defenses against conventional attacks are ineffective against our attacks.

Related papers

• Epistemic Reject Option Prediction [6.531546527140475]
  In high-stakes applications, predictive models must not only produce accurate predictions but also quantify and communicate their uncertainty.<n>Reject-option prediction addresses this by allowing the model to abstain when prediction uncertainty is high.<n>This is the first principled framework that enables learning predictors capable of identifying inputs for which the training data is insufficient to make reliable decisions.
  arXiv  Detail & Related papers  (2025-11-06T22:39:21Z)
• Countering adversarial evasion in regression analysis [0.7136933021609079]
  Adversarial evasion considers scenarios where adversaries adapt their data to influence particular outcomes from established prediction models.<n>This article serves to propose a pessimistic bilevel optimisation program for regression scenarios.
  arXiv  Detail & Related papers  (2025-09-26T09:35:26Z)
• Preliminary Investigation into Uncertainty-Aware Attack Stage Classification [81.28215542218724]
  This work addresses the problem of attack stage inference under uncertainty.<n>We propose a classification approach based on Evidential Deep Learning (EDL), which models predictive uncertainty by outputting parameters of a Dirichlet distribution over possible stages.<n>Preliminary experiments in a simulated environment demonstrate that the proposed model can accurately infer the stage of an attack with confidence.
  arXiv  Detail & Related papers  (2025-08-01T06:58:00Z)
• Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models [12.524811181751577]
  We propose a novel optimization for adversarial attacks against BCSD models.<n>In particular, we aim to improve the attacks in a challenging scenario, where the attack goal is to limit the model predictions to a specific range.<n>Our attack leverages the superior capability of black-box, model-agnostic explainers in interpreting the model decision boundaries.
  arXiv  Detail & Related papers  (2025-06-05T08:29:19Z)
• On Transfer-based Universal Attacks in Pure Black-box Setting [94.92884394009288]
  We study the role of prior knowledge of the target model data and number of classes in attack performance.<n>We also provide several interesting insights based on our analysis, and demonstrate that priors cause overestimation in transferability scores.
  arXiv  Detail & Related papers  (2025-04-11T10:41:20Z)
• On the Robustness of Adversarial Training Against Uncertainty Attacks [9.180552487186485]
  In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty.<n>In this work, we reveal both empirically and theoretically that defending against adversarial examples, i.e., carefully perturbed samples that cause misclassification, guarantees a more secure, trustworthy uncertainty estimate.<n>To support our claims, we evaluate multiple adversarial-robust models from the publicly available benchmark RobustBench on the CIFAR-10 and ImageNet datasets.
  arXiv  Detail & Related papers  (2024-10-29T11:12:44Z)
• Adversarial Attacks Against Uncertainty Quantification [10.655660123083607]
  This work focuses on a different adversarial scenario in which the attacker is still interested in manipulating the uncertainty estimate. In particular, the goal is to undermine the use of machine-learning models when their outputs are consumed by a downstream module or by a human operator.
  arXiv  Detail & Related papers  (2023-09-19T12:54:09Z)
• Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving [18.72382517467458]
  We propose a novel adversarial backdoor attack against trajectory prediction models. Our attack affects the victim at training time via naturalistic, hence stealthy, poisoned samples crafted using a novel two-step approach. We show that the proposed attack is highly effective, as it can significantly hinder the performance of prediction models.
  arXiv  Detail & Related papers  (2023-06-27T19:15:06Z)
• Re-thinking Data Availablity Attacks Against Deep Neural Networks [53.64624167867274]
  In this paper, we re-examine the concept of unlearnable examples and discern that the existing robust error-minimizing noise presents an inaccurate optimization objective. We introduce a novel optimization paradigm that yields improved protection results with reduced computational time requirements.
  arXiv  Detail & Related papers  (2023-05-18T04:03:51Z)
• On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach [42.81632484264218]
  In machine learning models, perturbations of fractions of the training set (poisoning) can seriously undermine the model accuracy. This paper aims to implement a novel hash-based ensemble approach that protects random forest against untargeted, random poisoning attacks.
  arXiv  Detail & Related papers  (2022-09-28T11:41:38Z)
• Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving [77.39239190539871]
  We show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving. We introduce a new uncertainty measure based on disagreeing predictions as measured by a dissimilarity function. We show experimentally that our proposed approach is much less computationally intensive at inference time than competing methods.
  arXiv  Detail & Related papers  (2021-05-28T09:23:05Z)
• DEUP: Direct Epistemic Uncertainty Prediction [56.087230230128185]
  Epistemic uncertainty is part of out-of-sample prediction error due to the lack of knowledge of the learner. We propose a principled approach for directly estimating epistemic uncertainty by learning to predict generalization error and subtracting an estimate of aleatoric uncertainty.
  arXiv  Detail & Related papers  (2021-02-16T23:50:35Z)
• Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions [121.10450359856242]
  We develop a frequentist procedure that utilizes influence functions of a model's loss functional to construct a jackknife (or leave-one-out) estimator of predictive confidence intervals. The DJ satisfies (1) and (2), is applicable to a wide range of deep learning models, is easy to implement, and can be applied in a post-hoc fashion without interfering with model training or compromising its accuracy.
  arXiv  Detail & Related papers  (2020-06-29T13:36:52Z)

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.