arXiv subjects

Tudor Cebere

Publications and source records attributed to Tudor Cebere.

8 recordsLinked to original sources

arXiv2026

Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees

Random forests are widely used in fields involving sensitive tabular data, but existing approaches to enforcing differential privacy (DP) typically degrade performance to the point of impracticality. In this paper, we introduce Lumberjack, a differentially private random forest algorithm that achieves substantially higher utility by constructing large random decision trees and then applying aggressive, privacy-preserving pruning to retain only sufficiently populated nodes. A key component of our approach is a novel $(\varepsilon,\delta)$-DP heavy hitter detection algorithm for hierarchical data, whose error is $O_{\varepsilon,\delta}(\sqrt{\log h})$ for trees of height $h$ and may be of independent interest. This favorable scaling enables the use of significantly deeper trees than in prior work, leading to improved expressiveness under privacy constraints. Our empirical evaluation on benchmark datasets shows that Lumberjack consistently outperforms prior DP random forest methods, establishing a new state of the art. In particular, our approach yields substantial improvements in the privacy-utility trade-off for practical privacy budgets. Our findings suggest that carefully designed DP random forests can close much of the utility gap, highlighting a promising and underexplored direction for future research.

cs.LG↗

arXiv2026

Privacy Auditing with Zero (0) Training Run

Privacy auditing provides empirical lower bounds on the differential privacy parameters of learning algorithms. Existing methods, however, require interventional access to the training pipeline, either to retrain models multiple times or to randomize data inclusion. This is often infeasible for large and opaque deployed systems such as foundation or language models. We introduce Zero-Run privacy auditing, a framework for auditing models post-hoc using two fixed datasets: examples known to be training-set members and examples known to be non-members. In this observational regime, membership is no longer randomized; instead, member and non-member data often differ in distribution, so membership inference scores may reflect a distribution shift rather than algorithmic leakage. Drawing on ideas from causal inference, we formalize this confounding effect and propose two complementary corrections that yield valid privacy audits. Our first approach models the combined effect of distribution shift and algorithmic leakage as an adaptive composition, producing conservative global corrections. Our second approach conditions on observed data and adjusts pointwise membership guesses, yielding sharper instance-dependent bounds. Experiments on synthetic data and large-scale image and text models show that Zero-Run auditing enables practical privacy evaluation when retraining or controlled data insertion is infeasible.

cs.CR↗

arXiv2026

Privacy in Theory, Bugs in Practice: Grey-Box Auditing of Differential Privacy Libraries

Differential privacy (DP) implementations are notoriously prone to errors, with subtle bugs frequently invalidating theoretical guarantees. Existing verification methods are often impractical: formal tools are too restrictive, while black-box statistical auditing is intractable for complex pipelines and fails to pinpoint the source of the bug. This paper introduces Re:cord-play, a gray-box auditing paradigm that inspects the internal state of DP algorithms. By running an instrumented algorithm on neighboring datasets with identical randomness, Re:cord-play directly checks for data-dependent control flow and provides concrete falsification of sensitivity violations by comparing declared sensitivity against the empirically measured distance between internal inputs. We generalize this to Re:cord-play-sample, a full statistical audit that isolates and tests each component, including untrusted ones. We show that our novel testing approach is both effective and necessary by auditing 12 open-source libraries, including SmartNoise SDK, Opacus, and Diffprivlib, and uncovering 13 privacy violations that impact their theoretical guarantees. We release our framework as an open-source Python package, thereby making it easy for DP developers to integrate effective, computationally inexpensive, and seamless privacy testing as part of their software development lifecycle.

cs.CR↗

arXiv2026

Causal Evaluation of Membership Inference Attacks

Membership Inference Attacks (MIAs) aim to distinguish training points (members) from unseen data (non-members), and are widely used to quantify memorization and assess privacy risks. Standard MIA evaluation requires repeated retraining, which is computationally costly for large models. One-run (single training with randomized data inclusion) and zero-run (post hoc evaluation) methods are often used instead, but their statistical validity remains unclear. We address this gap by framing MIA evaluation as a causal inference problem, defining \emph{memorization as the causal effect of including a data point in the training set}. This novel formulation reveals and formalizes key sources of bias in existing protocols: one-run methods suffer from interference between jointly included points, while zero-run evaluations are additionally confounded by distribution shift between member and non-member evaluation data. We derive causal analogues of standard MIA metrics and propose practical estimators for multi-run, one-run, and zero-run regimes with non-asymptotic consistency guarantees. We validate our approach in several settings, including pretrained and fine-tuned LLMs, showing that it enables reliable measurement of MIA performance without retraining and under distribution shift. Overall, our framework provides a principled foundation for privacy evaluation in modern AI systems.

cs.LG↗

arXiv2025

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

Machine learning models can be trained with formal privacy guarantees via differentially private optimizers such as DP-SGD. In this work, we focus on a threat model where the adversary has access only to the final model, with no visibility into intermediate updates. In the literature, this hidden state threat model exhibits a significant gap between the lower bound from empirical privacy auditing and the theoretical upper bound provided by privacy accounting. To challenge this gap, we propose to audit this threat model with adversaries that craft a gradient sequence designed to maximize the privacy loss of the final model without relying on intermediate updates. Our experiments show that this approach consistently outperforms previous attempts at auditing the hidden state model. Furthermore, our results advance the understanding of achievable privacy guarantees within this threat model. Specifically, when the crafted gradient is inserted at every optimization step, we show that concealing the intermediate model updates in DP-SGD does not enhance the privacy guarantees. The situation is more complex when the crafted gradient is not inserted at every step: our auditing lower bound matches the privacy upper bound only for an adversarially-chosen loss landscape and a sufficiently large batch size. This suggests that existing privacy upper bounds can be improved in certain regimes.

cs.LG↗

arXiv2025

Private Rate-Constrained Optimization with Applications to Fair Learning

Many problems in trustworthy ML can be expressed as constraints on prediction rates across subpopulations, including group fairness constraints (demographic parity, equalized odds, etc.). In this work, we study such constrained minimization problems under differential privacy (DP). Standard DP optimization techniques like DP-SGD rely on objectives that decompose over individual examples, enabling per-example gradient clipping and noise addition. Rate constraints, however, depend on aggregate statistics across groups, creating inter-sample dependencies that violate this decomposability. To address this, we develop RaCO-DP, a DP variant of Stochastic Gradient Descent-Ascent (SGDA) that solves the Lagrangian formulation of rate constraint problems. Through careful design, the extra privacy cost incurred by incorporating these constraints in our approach is limited to that of privately estimating a histogram over each mini-batch at every step. We prove the convergence of our algorithm through a novel analysis of SGDA that leverages the linear structure of the dual parameter. Empirical results show that our method Pareto-dominates existing private learning approaches under group fairness constraints and also achieves strong privacy-utility-fairness performance on neural networks.

cs.LG↗

arXiv2021

Syft 0.5: A Platform for Universally Deployable Structured Transparency

We present Syft 0.5, a general-purpose framework that combines a core group of privacy-enhancing technologies that facilitate a universal set of structured transparency systems. This framework is demonstrated through the design and implementation of a novel privacy-preserving inference information flow where we pass homomorphically encrypted activation signals through a split neural network for inference. We show that splitting the model further up the computation chain significantly reduces the computation time of inference and the payload size of activation signals at the cost of model secrecy. We evaluate our proposed flow with respect to its provision of the core structural transparency principles.

cs.LG↗

arXiv2021

PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN

We introduce PyVertical, a framework supporting vertical federated learning using split neural networks. The proposed framework allows a data scientist to train neural networks on data features vertically partitioned across multiple owners while keeping raw data on an owner's device. To link entities shared across different datasets' partitions, we use Private Set Intersection on IDs associated with data points. To demonstrate the validity of the proposed framework, we present the training of a simple dual-headed split neural network for a MNIST classification task, with data samples vertically distributed across two data owners and a data scientist.

cs.LG↗