Overview

Differential privacy studies algorithms whose outputs reveal limited information about any individual record, even when an attacker knows other data. Common approaches add calibrated noise to statistics or clipped gradients, use randomized response for local privacy, or combine privacy with subsampling, shuffling, and secure aggregation. These methods support private statistical estimation, machine learning, federated learning, and synthetic data generation, including for images, tables, and text; evaluation often measures both task utility and membership-inference risk. A central tension is that stronger guarantees can reduce accuracy or increase computational cost, while task-specific structure and tighter privacy accounting may improve the trade-off without resolving all deployment risks.

Latest papers

314 papers39 papers in the last four weeks, up 5% on the four weeks before. 0.3% of all new papers.

Oct 5, 2026

Private online learning and prediction for Littlestone classes

We study mistake bounds for differentially private online learning and online prediction under oblivious realisable adversaries. Online learning requires the learner to release a hypothesis at each time step whereas in online prediction, the learner only needs to make predictions without releasing a hypothesis. Using a novel lower bound for private online learning and an upper bound for private prediction, we show that the sample complexity of these two problems are separated by a factor that grows with the time horizon for every class of finite Littlestone dimension dd. First, we prove that every (ε,δ)(ε,δ)-private online learner has a deterministic realisable stream of length TT on which the mistake bound is at least E[MT]=O(dεlog⁡2/3T)\mathbb E [M_T]= O\left(\frac dε\log^{2/3} T\right). In particular, this is the first non-trivial lower in the range 1/T<δ<1/log⁡T)1/T<δ<1/\log T) left open in earlier works[SR22,DSS24,LWY24]. Second, we prove that for every class of of Littlestone dimension dd, there exists an (ε,δ)(ε,δ)-jointly private predictor with at most 22cd2ε−2log⁡2(2/(εδ))2^{2^{cd^2}}ε^{-2}\log^2(2/(εδ)) expected mistakes, independently of TT, for some absolute constant c>0c>0. Thus, for every fixed class of finite Littlestone dimension when δ=Θ(1/log⁡T)δ=Θ(1/\log T), private learning requires O(log⁡2/3T)O\left(\log^{2/3} T\right) expected mistakes, whereas private prediction admits O(log⁡log⁡T2)O(\log\log T^2).
Oct 5, 2026

Differentially Private Mixing of Public Datasets Improves Private Learning

Many machine learning applications involve sensitive data and therefore require training under differential privacy (DP). However, DP training often degrades model utility. In some cases, first pre-training the model on "public" data before finetuning with DP on the sensitive data can reduce the drop in utility. However, the success of this depends on how relevant the selected public dataset is to the sensitive data. We introduce the first pipeline that privately learns the mixture of several public datasets to pretrain on for a given sensitive downstream task. Our key insight is that we can privately find the best mixture of multiple public datasets by privately learning a low-dimensional linear model. We tested our method on the NIH dataset for X-ray classification and the ENRON email dataset for language modeling. Applying our method to find tailored mixtures of X-ray datasets to pretrain on for diseases in the NIH ChestX-ray14 dataset, we improved macro AUC by up to 0.037 across privacy budgets compared to the baselines, with gains as large as +22.8% relative AUC on Cardiomegaly at ε=1ε=1. For DP training on the ENRON dataset, pre-training on our mixture of The Common Pile (a collection of public-domain text datasets) decreased test perplexity by 16% relative to the baseline mixtures.
Oct 5, 2026

DP-ES: Differentially Private Evolution Strategies for Prompt Optimization

Token-level differentially private (DP) prompt optimization methods such as DP-OPT can become unstable under tight privacy budgets: on GSM8K, DP-OPT obtains 49.5±28.5%49.5\pm28.5\% across 30 runs, and a logged search trajectory reveals prompt-template drift and noise-sensitive irreversible choices. We diagnose these as structural consequences of greedy token-by-token construction over privately aggregated counts. We then propose DP-ES (Differentially Private Evolution Strategies), a structurally cleaner alternative that maintains a population of full prompts, mutates them via LLM calls that never access the private dataset, and spends privacy only on sampled-Gaussian evaluation; deterministic or Gumbel-smoothed selection is post-processing. Under a conservative (ε≤1.0,δ=10−5)(\varepsilon\leq1.0,δ=10^{-5}) guarantee, DP-ES achieves 88.1% on GSM8K (+38.6 pp over DP-OPT, approximately 9 times lower standard deviation), 99.7% on MedQA, 73.5% on BANKING77, and 86.8% on Alpaca. It is also 2.5 times faster in wall-clock time and uses 3.3 times fewer logged private-data call groups than DP-OPT. Selection and population ablations, implementation-level noise checks, and a 200-profile exact-match memorization stress test complement the formal guarantee. Scope: Our experiments establish optimization robustness under DP noise, especially where prompt structure is critical; end-to-end validation on genuinely sensitive, non-saturated deployment data remains future work.
Oct 3, 2026

Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy

Best arm identification under differential privacy is a pure-exploration problem in which both statistical efficiency and privacy protection must be achieved simultaneously. We study fixed-budget best arm identification for bandits under pure εε-differential privacy, where the learner must recommend an arm after a prescribed sampling budget while protecting the full transcript. We prove that the optimal exponential decay rate of the error probability is upper bounded by an instance-dependent privacy-aware transportation exponent that differs from the analogous quantity used to characterize the stopping time in fixed-confidence analysis by Jourdan and Azize [2025]. Guided by this exponent, we propose AO-Pri-BAI, an adaptive algorithm that maintains private running estimates through Laplace-tree mechanisms and learns a sampling design through a min--max interaction between hard alternatives and arm allocations. We prove that AO-Pri-BAI satisfies pure εε-differential privacy. We also establish that the exponent of the failure probability of AO-Pri-BAI matches the privacy-aware benchmark. Numerical studies show that even in the non-asymptotic setting, AO-Pri-BAI outperforms benchmark algorithms on various instances, complementing the theoretical analyses.
Oct 2, 2026

Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy

Multimodal 3D Human Pose Estimation (3D HPE) combines complementary information from RGB, LiDAR, and mmWave radar, but models trained on correlated observations from the same individuals, raise privacy risks overlooked by record level analysis. We present a unified framework for multimodal 3D HPE that couples kinematics-induced sensor fusion with subject level privacy auditing and private training. First, our multimodal model aligns modality specific joint representation, injects skeletal structure and adaptively aggregates complementary sensor evidence for accurate pose prediction. Second, we formulate a black-box subject membership inference attack for 3D HPE, complemented by an empirical pointwise maximal leakage analysis, which characterizes how individual attack score outcomes change inference about the membership outcome. Third, we instantiate user-level differential privacy via Action Temporal Stratification, a population weighted within-subject sampling strategy that enforces action and temporal coverage. We evaluate our framework on the MM-Fi dataset across three diverse experimental protocols. Source-code will be released upon acceptance.
Oct 2, 2026

Differential Privacy of Gradient Descent on Perturbed Objectives

Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer. We study the finite computation obtained by releasing the NN-th iterate of deterministic gradient descent on w↦F(w;S)+⟨z,w⟩w\mapsto F(w;S)+\langle z,w\rangle, where z∼N(0,σ2Id)z\sim\mathcal N(0,σ^2I_d) is drawn once before optimization. For strongly convex and smooth objectives with Lipschitz Hessian, we prove an explicit condition under which the map z↦wNz\mapsto w_N is a C1C^1-diffeomorphism on the bounded domains used in the privacy argument, with a quantitative lower bound on the smallest singular value of its Jacobian. This permits a direct change-of-variables analysis of the finite iterate. For generalized linear models, the resulting privacy-profile bound has no explicit ambient-dimension factor once the iteration condition holds, and its finite-iteration correction decreases geometrically. By letting the free truncation parameter grow slowly with NN, we recover the corresponding exact-minimizer certificate in the limit. We also bound the expected excess empirical risk by dσ2/(2μ)dσ^2/(2μ) plus a geometrically decreasing optimization term, and transfer the result to population risk without an additional multiplicative condition-number factor in the leading statistical terms.
Oct 1, 2026

HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems

Balancing electricity demand and supply is increasingly difficult due to the inherent intermittency of renewable power generation and the stochastic power consumption. Grid operators require fine-grained, decision-relevant insights into household energy consumption to manage peak loads and design responsive tariffs, but increased transparency at this level raises significant privacy concerns. Traditional methods for explainable AI (XAI) can reveal sensitive information, while standard privacy techniques often reduce the usefulness of explanations. To address this issue, we introduce HXAI, a hierarchical framework that preserves privacy while enabling reasonable explainable analysis for grid-level demand management. HXAI consists of two main components: (1) a local model that generates fine-grained explanations within a secure, private environment, and (2) a zonal model that aggregates these explanations to support grid-level analysis while enforcing privacy through flexible privacy-budget management. We explicitly limit cumulative privacy exposure under repeated operator queries and show that the proposed framework preserves decision-relevant information without compromising household privacy. Experiments on both simulated and real-world energy datasets demonstrate that HXAI provides useful insights for zonal load management while ensuring that appliance-level consumption remains local and is never transmitted to grid operators. Our results show that preserving the semantic structure of explanations, rather than minimizing numerical error, is the key to XAI under differential privacy. This framework provides a way to achieve both privacy and explainability in energy management.
Sep 30, 2026

Certification-Based Differentially Private Learning

Differential privacy (DP) in machine learning is typically achieved by adding noise to model parameters (private learning) or to model outputs (private prediction). Recent work uses formal methods, namely abstract interpretation, to provide tighter privacy guarantees, but only for private prediction in classification settings. In this work, we investigate the use of formal methods as a general tool for tighter privacy analysis. First, we generalize the abstract gradient training (AGT) framework to private prediction in continuous, unbounded regression. Second, by reducing learning in parameterized models to a regression problem over the parameter space, we introduce Abstract Gradient Sampling (AGS), an algorithm that enables reachability-based analysis to provide guarantees for private learning. In both private prediction and private learning, we provide tightened privacy accounting for the AGT framework and a theoretical analysis demonstrating when our smooth sensitivity upper-bounds yield favourable privacy-utility trade-off. In practice, we validate that our regression bounds are tighter than global-sensitivity baselines on regression benchmarks, and, notably, yield the first finite privacy guarantees in settings where global prediction sensitivity is a priori unbounded. We also find that under matched conditions, our private learning algorithm can outperform standard private learners.
Sep 30, 2026

PrivCert: Certifying Statement Support under Differential Privacy

Differentially private (DP) text generation can protect individual records, but privacy alone does not specify what evidence a released statement carries about the underlying data. We identify this as an evidence gap: a private report may contain plausible claims without indicating whether they are strongly supported by the private dataset. We introduce PrivCert, a framework for privacy-preserving reporting that makes statement support explicit through privacy-preserving certificates and emit-or-abstain decisions. As a canonical instantiation, PrivCert-PF (Proposal-and-Filter) separates data-independent candidate discovery from private support certification, emitting only statements whose support passes a private evidence test. We provide theoretical grounding for this framework by characterizing the limits of implicit evidence under DP, deriving a sharp privacy--honesty frontier for single-statement certification, and establishing a worst-case cost for fine-grained multi-statement certification. Experiments on synthetic tasks and TAB, WildChat, and Yelp show that explicit certification maintains low unsupported emission, while free-text DP baselines frequently produce low-support claims under the same declared support semantics. We further show that the PrivCert contract can be realized with histogram, sparse-vector, and Gaussian mechanisms, and use DP synthetic data to illustrate an important boundary: support in a private proxy does not automatically certify support in the original data. Together, these results position privacy-preserving reporting as an evidence-design problem: not only how to generate private text, but what a private report can substantiate about its underlying data.
Sep 29, 2026

Where Privacy Belongs: Placement Diagnosis and Certified Selection for Private Counterfactual Explanations on Graphs

Counterfactual explanations for graph neural networks (GNNs) find the minimal intervention that flips a node's prediction--but computing one requires reading sensitive graph structure, and releasing it discloses that structure. Both existing placements fail. Privatizing the graph before explaining corrupts the target on exactly the borderline nodes needing recourse, manufacturing spurious flips that flip the privatized graph but not the true one. Explaining on the clean graph and perturbing the released explanation resists certification: re-auditing the standard heuristic shows an implied full-release budget of 573--753 on Cora and 256 on CiteSeer--orders of magnitude beyond its advertised budget--with worst-case single-entry leakage at AUC 1.0. We propose PrivCFS, which replaces certification-by-optimization with certification-by-construction: counterfactual selection over a fixed, data-independent candidate universe--edge interventions from a public prior graph, feature interventions from a public schema--whose no-op semantics give neighboring graphs the same output support. A validity-gated, clipped utility of global sensitivity Δu≤1Δu \le 1 released through the exponential mechanism gives pure ε\varepsilon-DP for the complete released object, composable over queries--to our knowledge the first such guarantee on graphs. Privacy noise is the cheapest stage: at ε\varepsilon=8 the release retains 94--97% of its support-restricted non-private optimum on the recourse population and 83--95% on the general one; the optimal edge-inference audit attains AUC 0.50 on average and 0.59 worst-pair, versus the heuristic's worst entry 1.0; and transfers to a 15K-node graph at 0.96 valid rate. The dominant cost is a measurable, monotone price in public disclosure, readable off one table before any budget is spent--turning explanation privacy from an accounting risk into a purchasable decision.
Sep 29, 2026

A Sharp Transition in Data Reconstruction under Differential Privacy

Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivating defenses with guarantees that remain valid against future threats. While differential privacy (DP) provides formal protection, choosing the privacy budget remains a challenge: small budgets severely reduce utility, but it is hard to quantify how large the budget can be without allowing accurate reconstruction. In this work, we study informed attackers who aim to reconstruct a single dd-dimensional training sample from a ρρ-zero-concentrated DP model, knowing all other training data. Our main contribution is to establish a sharp transition at ρ≍dρ\asymp d for data reconstruction: on the one hand, we derive entropy-based lower bounds for any private mechanism and any attack, characterizing a set of target priors for which reconstruction is information-theoretically impossible for ρ≪dρ\ll d; on the other hand, we analyze a simple attack on private linear regression with output perturbation, showing that reconstruction is practically feasible for ρ≫dρ\gg d. Remarkably, the transition moves to ρ≍sρ\asymp s for data lying in an ss-dimensional subspace, demonstrating that the privacy budget guaranteeing adequate protection must be assessed in terms of the effective dimension of the data. We validate our findings via experiments on synthetic data and natural images (CIFAR-10, ImageNet).
Sep 29, 2026

Understanding Private Evolution as Learning-Augmented Clustering

Private Evolution (PE) is a differentially private algorithm for synthetic data generation. While it can be viewed as a Wasserstein learning algorithm, it performs much better in practice than worst-case Wasserstein analyses would predict. We recast PE as generative model-augmented Wasserstein learning. We show theoretically that when we take into account the use of a generative model that is able to capture something about the true distribution, then we can obtain much better performance bounds. For example, if the generator gives samples in the same low-dimensional space as the distribution, then sample complexity depends on intrinsic, not ambient, dimension. We also show that standard variants of PE can fail to converge on simple well-clustered instances, and propose a new geometry-aware version of PE with provable convergence on such instances. Experimentally, we show that our new algorithm is competitive with standard baselines and can improve recall.
Sep 27, 2026

Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits

Can vanilla policy optimization explore enough to achieve near-optimal regret in stochastic contextual bandits? We show that standard exponential policy updates driven by offline regression do so under realizability, without exploration bonuses or importance weighting. For AA actions, TT rounds, and a finite prediction class FF, vanilla PO achieves O~(ATlog⁡(∣F∣))\widetilde O(\sqrt{AT\log(|F|)}) regret with high probability. Our analysis reveals an implicit exploration mechanism of independent interest: gradual policy updates prevent actions from losing probability too quickly, allowing the regression oracle to learn their expected losses. We further develop a batched version using only O(log⁡T)O(\log T) regression calls and policy switches, and show how private regression oracles yield differentially private contextual bandit algorithms without composition across batches. For a finite class, this gives pure εpriv\varepsilon_{\rm priv}-DP and regret O~(ATlog⁡(∣F∣/δ)(1+εpriv−1/2))\widetilde O\left( \sqrt{AT \log(|F|/δ)}(1+\varepsilon_{\rm priv}^{-1/2}) \right). Finally, experiments across oracle-based contextual bandit algorithms, with and without privacy, demonstrate the practical effectiveness of policy optimization and the value of explicit exploration under stronger privacy constraints.
Sep 27, 2026

Geometry-Adaptive Mechanisms for Private Synthetic Data

Generating differentially private synthetic data with meaningful Wasserstein utility guarantees is challenging in high dimensions. For datasets of size nn on [0,1]d[0,1]^d with d≥2d\ge2, existing pure ε\varepsilon-differentially private mechanisms achieve expected 11-Wasserstein error of order (εn)−1/d(\varepsilon n)^{-1/d}, reflecting the curse of dimensionality. While this rate is optimal in the worst case, it can be overly pessimistic when the data are supported on a lower-dimensional set. We formalize this through a multiscale packing-growth dimension kk, which captures the geometric complexity of the support via the growth of packing numbers across scales. We propose Adaptive Pruned-PMM, a pure ε\varepsilon-differentially private mechanism that combines private depth selection with our pruned variant of the Private Measure Mechanism (PMM) of He et al.\ (2023). The mechanism supports deeper, geometry-adapted hierarchies with expected running time O ⁣(d(n+d)log⁡(εn))O\!\left(d(n+d)\log(\varepsilon n)\right), which is near-linear in nn for fixed dimension and privacy budget. Under an external multiscale packing-growth condition with dimension kk, we show that, for fixed positive privacy budgets and fixed geometry, the expected 11-Wasserstein error is of order (εn)−1/k(\varepsilon n)^{-1/k} for k>1k>1 as nn grows. We also prove a lower bound under a corresponding internal packing-growth condition, showing that the exponent 1/k1/k is sharp within this framework.
Sep 25, 2026

Gap-free Differentially Private PCA for Gaussian Data

We give a gap-free (ε,δ)(ε,δ)-differentially private algorithm for the principal component analysis (PCA) problem with Gaussian data. The algorithm is based on a private variant of the power iteration method, and it is computationally efficient.
Sep 24, 2026

Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores

We formalize slate recommendation as a randomized score learner followed by deterministic selection. First, an appropriately scoped differential-privacy guarantee passes through selection and its audit trace by post-processing. End-to-end privacy holds only when selector inputs are public or independent, previous private outputs, or separately privacy-accounted; fixing raw state or candidate information instead yields only a conditional guarantee. Second, we derive a logged margin certificate: bounded score-induced objective movement below half the smallest greedy decision margin guarantees that the ordered slate is unchanged. Controlled fixed-margin tests show near-linear exponent scaling, with an empirical slope of −0.220-0.220 (95% CI [−0.231,−0.210][-0.231,-0.210]) against the independent-noise reference −1/4-1/4. Real-anchor experiments on OULAD, MovieLens-25M, and Amazon Musical Instruments show that greater anchor weight reduces score-noise-induced ranking churn. OULAD and EdNet certificate checks validate the implementation of the logged inequality, while closed-loop simulations show bounded target drift and setting-dependent downstream utility. The contribution is therefore a privacy-scope contract and a certifiable score-to-slate stability mechanism, not a universal utility claim.
Sep 23, 2026

Private Decentralized Optimization with Noise Reduction and Bias Correction

Private decentralized learning is affected by sampling noise, privacy noise, and decentralized bias under heterogeneous data. We propose Private Recursive Decentralized Optimization (PRDO). PRDO uses recursive estimation with same-batch gradient differences to reduce estimation errors caused by sampling and privacy noise, while its Exact Diffusion component corrects decentralized bias arising from data heterogeneity. Our analysis establishes a nonconvex convergence bound without assuming uniformly bounded data heterogeneity across nodes. It further gives a sufficient condition under which recursive gradient differences yield strictly lower query sensitivity than private Exact Diffusion, together with an example that rigorously satisfies this condition. Experiments show improved accuracy over the evaluated baselines.
Sep 22, 2026

An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting

The goal of this note is to give a detailed proof, to the best of our understanding, of the recent presentation by Harrison and Leeman (arXiv:2609.17650v01 and arXiv:2609.17650v02) of the proof by Astra on the lower bound for differentially private continual counting. We believe a more natural and easy proof is possible and hope that this note will help in that effort. Prior to the initial preprint by Harrison and Leeman (arXiv:2609.17650v01), Bairaktari and Larsen (arXiv:2607.00876) gave an elegant proof to show a lower bound of Ω(log⁡3/2(n))Ω(\log^{3/2}(n)) for both pure and approximate-DP continual counting, and in personal communication had informed us that they have a proof of optimal Ω(log⁡2(n))Ω(\log^{2}(n)) for pure-differential private continual counting as well. They have subsequently published their Ω(log⁡2(n))Ω(\log^{2}(n)) bound, which is now a joint work of Bairaktari, Dahl, and Larsen (arXiv:2607.00876v3). Their new result is an elegant extension of their technique for approximate-differential privacy. Although the two proofs are technically different, the Astra argument uses related tree geometry introduced in Bairaktari and Larsen.
Sep 22, 2026

Gap-Free Streaming PCA Beyond Rank-One Updates: Near-Optimal Rates and Applications to Differential Privacy

Streaming principal component analysis (PCA) seeks to recover a leading spectral subspace in a single pass over a data stream. We give a new analysis of the ubiquitous Oja's algorithm [Oja82] for the most general, gap-free variant of this problem, where no eigengap assumptions are made on the underlying mean matrix, complemented by a nearly-matching lower bound. Prior works achieving near-optimal rates for streaming PCA either required gap assumptions [JJK+16, HNWW21], or were limited to rank-one updates [AZL17, Lia23]. Our proof only uses a second moment bound on the individual stochastic updates, bypassing the almost sure bounds needed by prior near-optimal analyses, and the analogous offline matrix Bernstein bound. We also extend our result to a Rayleigh quotient notion of approximate PCA, addressing an open question of [JJK+16]. As our main application, we give gap-free differentially private PCA guarantees for sub-Gaussian data, settling Conjecture 1.1 of [Bro26] up to logarithmic factors.
Sep 21, 2026

Empirical Auditing of Edge-Private Graph Generators

We empirically audit privacy leakage by testing whether outputs from edge-neighbouring inputs remain distinguishable, using statistically valid lower bounds on the privacy loss witnessed by our attacks. Our framework compares direct-edge, local-structural, and GNN-based attacks through the geometry surrounding a target edge. Experiments across two generators and two networks show that privacy leakage is both mechanism- and network-dependent, with learned representations revealing information not captured by conventional local statistics.
Sep 19, 2026

Improved Private Sparse Covariance Estimation with Multiscale Threshold Tests

We study differentially private covariance estimation in operator norm for mean-zero sub-Gaussian distributions with unknown covariance support and at most kk nonzero entries per row. We develop a multiscale random-threshold algorithm with sample complexity \ot(k2/α2+kd/(αε))\ot(k^2/α^2+k\sqrt d/(α\varepsilon)) for (ε,δ)(\varepsilon,δ)-differential privacy and error at most ασ2ασ^2, where dd is the dimension and σσ is a known sub-Gaussian scale. The bound improves the privacy-dependent term of the existing \ot(k2/α2+k3/2d/(αε))\ot(k^2/α^2+k^{3/2}\sqrt d/(α\varepsilon)) \citep{kumar2026curse} upper bound by a factor of k\sqrt k, and matches the lower bound of Ω~(k2/α2+kd/(αε))\widetildeΩ(k^2/α^2 + k\sqrt{d}/(α\varepsilon)) in its applicable parameter regime. Our key technical ingredient is a direct operator-norm bound on the centered fluctuations of an ideal reconstruction, exploiting conditional independence rather than accumulating entrywise errors across each row. A multiscale allocation of threshold tests balances reconstruction variance against query sensitivity. Together, these ingredients sharpen the trade-off between approximation error and privacy protection, removing the additional k\sqrt{k} factor from the privacy-dependent sample complexity.
Sep 18, 2026

Locally Private Inference for Riemannian Stochastic Optimization

We develop inference for manifold-valued population minimizers when each observation belongs to a different participant and only locally private messages reach the analyst. The method releases randomized tangent gradients and combines them through Riemannian stochastic approximation and Polyak-Ruppert averaging. Directly inserting a private data surrogate into a nonlinear loss can shift its population target, whereas conditional centring of the released gradient preserves the first-order equation. We introduce symmetric-pair regression (SPR) to estimate the asymptotic variance from the same private messages used for point estimation, without holding out participants or requesting a second release. We prove the central limit theorem and consistency of the fully transcript-based sandwich covariance and intrinsic Wald region under local differential privacy. Simulations across various statistical problems and manifolds support the predicted decrease in estimation error and near-nominal coverage under moderate privacy. An application to NHANES anthropometric data illustrates private estimation of a leading body-size direction and its uncertainty.
Sep 14, 2026

Differentially Private Semantic Plans for Aggregate Insight Generation

URANIA provides end-to-end differential privacy (DP) for summaries of data-dependent clusters. However, its cluster--keyword release does not directly provide collection-wide aggregates for semantic concepts defined independently of the protected corpus. Records may express several concepts, records expressing the same concept may be assigned to different clusters, and cluster identities need not correspond across analyses. Consequently, cluster-level statistics do not directly provide comparable measurements of predefined concepts across collections or repeated analyses. We introduce DP-SPIN, a trusted-curator framework for aggregate measurement and summarization over semantic concepts fixed independently of the protected target records. Each record is mapped to a bounded sparse nonnegative vector over these concepts, whose sum forms a semantic sketch. A differentially private mechanism releases a semantic plan containing admitted concepts and noisy masses; normalized semantic-support values and support bins are obtained by post-processing. For user-level privacy, each user's aggregate contribution is clipped to a fixed bound. The language model receives only the plan and fixed decoding instructions, while a public verifier checks concept mentions, reported values, comparisons, and rank claims against the released plan. The final summary is differentially private by post-processing. We establish record- and user-level DP guarantees under add/drop and replacement adjacency. We evaluate DP-SPIN under record-level privacy on CFPB complaint narratives, Amazon All Beauty reviews, and Yelp restaurant reviews, and under user-level privacy on Amazon and Yelp. We compare DP-SPIN with non-private plan and summary references, DP keyword and category histogram baselines, and a URANIA-style baseline with a fixed public keyword vocabulary.
Sep 14, 2026

Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation

This study proposes a privacy-enhanced federated learning framework to address secure collaborative training in distributed data environments. The framework integrates Dynamic Differential Privacy (DDP), lightweight Homomorphic Encryption (HE), and Local Differential Privacy (LDP) mechanisms to ensure data privacy protection during model training. Additionally, the framework employs an asynchronous aggregation strategy with version control to support distributed training in asynchronous environments. Experimental validation on the CIFAR-10 and Purchase-100 benchmark datasets demonstrates that the method maintains high classification accuracy (up to 82.6%) even under stringent privacy constraints (ε = 0.1), while reducing communication overhead by 21.3% compared to FedAvg. Experimental results demonstrate that this framework effectively balances privacy protection and model performance in distributed machine learning scenarios, providing a scalable technical foundation for large-scale distributed collaborative computing.
Sep 14, 2026

SpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy

User prompts provided to large language models (LLMs) may contain private information. One way to protect them is to execute the LLM inside a trusted execution environment (TEE). However, this results in slow inference times as current TEEs are significantly slower than GPUs for LLM inference. To circumvent this, Tramèr and Boneh (2019) proposed Slalom which splits neural network inference between a TEE and an untrusted GPU. They encrypt inputs to computations outsourced to the GPU. In this paper, we extend this split-inference architecture to LLM inference and instead protect intermediate inputs using differential privacy (DP). We first demonstrate that masking intermediate representations is necessary by showing an 80% accuracy on a prompt-reconstruction attack from these representations. Our main contribution is a global sensitivity analysis of key functions in LLM inference, which bounds the required scale of DP noise. Unlike encryption, DP avoids quantization, allowing the LLM to remain in the floating-point domain. We also derive an upper bound on the floating-point error from masking and subsequent noise cancellation as a function of the privacy parameter epsilon, keeping the same quality of the LLM response. We implement our architecture using the Intel TDX TEE and two LLMs: Llama-3.2-3B and Qwen3-4B. Our split execution is nearly twice as fast as fully TDX-based inference. Moreover, it is at most 43% faster than Slalom while achieving higher accuracy. Finally, we demonstrate that prompt reconstruction, even with knowledge of the DP mechanism, cannot recover more information than is contained in an unrelated prompt.
Sep 13, 2026

Privacy Preserving Gossip Learning

We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learned sequentially, and each update must preserve the endpoint mappings at previously learned samples while protecting private data. This gives each agent three roles: (i) a learner that updates the model parameters, (ii) a teacher whose sample is learned at the current iteration, and (iii) a protected agent whose sample has already been learned. We build on Tuning without Forgetting (TwF) method to preserve previously learned mappings and show that TwF provides an indistinguishability guarantee for the learner whenever the set of protected agents contains another sample with the same label. For the teacher, we formulate a minimax optimal control problem that models the differential privacy noise as a worst-case disturbance to prevent performance loss while maintaining the same level of privacy for the gradient. For the protected agents, we compute the projections locally and aggregate them using a private push-sum gossip protocol. We prove geometric convergence of the decentralized gossip algorithm and of the distributed projection for TwF.
Sep 10, 2026

Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology

Clinical electroencephalography (EEG) data are valuable for healthcare research and for developing artificial intelligence (AI)-based clinical decision-support systems, but EEG recordings and derived features may contain sensitive patient-specific information. This creates privacy risks when data are reused, analyzed, or shared across clinical and research environments. Conventional anonymization methods are often insufficient for high-dimensional biomedical signals, since removing direct identifiers does not necessarily prevent re-identification, linkage, or inference risks. At the same time, strong privacy protection may distort clinically relevant signal characteristics and reduce data utility. This paper studies subject-level differential privacy for protecting clinical EEG-derived feature representations using Gaussian and Laplace perturbations. The proposed framework considers three deployment scenarios: client-side anonymization, centralized server-side anonymization, and decentralized local training. Following EEG preprocessing and feature extraction, Gaussian and Laplace perturbations are applied to the resulting patient-level EEG feature representations. The Laplace experiments evaluate the implemented noise scales, while the scales required for formal full-vector calibration are derived separately. The effects of both perturbations are assessed using statistical utility measures and a downstream machine-learning-based utility check. The results show that differentially private perturbation can be integrated into EEG processing workflows, but the selected mechanism, privacy parameters, and sensitivity calibration strongly influence data utility. The study highlights the practical privacy-utility trade-off in DP-based EEG feature anonymization and the challenges of preserving downstream utility in small and imbalanced clinical EEG datasets.
Sep 10, 2026

Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs

Per-layer differential privacy (DP) clipping improves gradient fidelity in federated learning by allocating per-matrix clipping budgets proportional to parameter count. We show that this recipe breaks for speech large language models (speech-LLMs), when the acoustic encoder and the language decoder differ by an order of magnitude in update norm. Single-pool per-layer methods suffer cross-component budget collapse, dragging word error rate (WER) far from flat global clipping or collapsing training entirely. When the norm imbalance is milder, adaptive single-pool methods partially recover, confirming that collapse severity scales with the inter-component norm ratio. We empirically diagnose the root cause across six per-layer methods and three speech-LLM architectures. We then propose \emph{αα-split}, a two-pool allocation that normalises encoder and LLM parameters into independent pools, and show that joint ℓ2\ell_2 sensitivity and the original (ε,δ)(\varepsilon,δ)-DP guarantee are unchanged. At architecture-calibrated αα, our method recovers WER utility compared to flat DP, while granting the encoder 4.47×4.47{\times} tighter per-component noise protection against speaker voice-based gradient-inversion attacks at only +2.6%+2.6\% LLM noise overhead.
Sep 9, 2026

Subgroup Membership Inference Audits of Differentially Private Synthetic Text

Synthetic data releases are increasingly proposed in the literature as a means of sharing realistic data replicas in lieu of sensitive private datasets. Even when the worst-case privacy leakage of such releases is bounded by means of differential privacy (DP), in practice a residual risk remains. Membership inference attack (MIA) audits are conducted to empirically quantify this risk. However, existing methods only measure average-case risk for randomly drawn records, which might conceal the risk to vulnerable subgroups. To highlight this issue, we define a subgroup-targeted membership inference game in which the target pool is an explicit parameter, and instantiate it with an audit of 32 proxies under three scenarios with different levels of attacker knowledge, across four datasets, three generators (DP-SGD fine-tuning, API-based prompting, and activation steering), and five privacy budgets. The audit shows that synthetic releases leak subgroup membership and that prior attacks systematically underestimate this leakage. DP is effective at the aggregate level: it substantially reduces average leakage at every budget we test. Three observations temper this picture. First, the remaining leakage is concentrated rather than spread out: under DP, a tenth of the records carries roughly 40% of it. Second, the protection DP delivers in practice is uneven: within its worst-case guarantee, the noise removes more of the measured leakage from random records than from high-risk ones---and a merged-pool audit that scores both record types against shared negatives confirms this at the record level. Third, which records leak proves to be a property of the release mechanism rather than of the record alone, so record-level risk cannot be assessed independently of the release.
Sep 8, 2026

Differentially Private Average Treatment Effect Estimation by Propensity Score Blocking

Average treatment effect (ATE) estimation in observational studies is a fundamental statistical tool used frequently in social science, medicine, and other fields. These fields often work with sensitive data where privacy protections are important, so a differentially private mechanism for ATE estimation is highly desirable. Here we present two propensity score-based algorithms for ATE estimation on observational data, one improving the inverse probability weighting (IPW) method used in prior work, and the other using blocking on the propensity score (BPS). Both show lower error and less bias than prior work, with the BPS-based algorithm frequently reducing error by 75% or more compared to prior work.