The paper introduces PostRI, a novel method that allows for computing a Randomization Interval (RI) for differentially private median queries after the median has already been estimated, significantly…

The paper proposes a RADIUS-based framework to maintain persistent device identity for Network Access Control (NAC) despite modern operating system MAC address randomization, ensuring regulatory compl…

The paper shows that deterministic cache eviction cannot ensure consistent serving-time error estimation and proposes a randomized approach to restore identifiability and provide error certificates.

This paper introduces a novel algorithm for generating k Hamming weight binary words in linear time while minimizing random bit consumption.

The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.

The paper proposes a novel exponential mechanism using quadratic approximations to fine-tune machine learning models on sensitive data while providing strong differential privacy guarantees.

The polynomial-time low-degree conjecture, which predicts that low-degree indistinguishability, a uniform null distribution, permutation invariance, and independent resampling imply polynomial-time ha…

The paper introduces Balanced Iteration Subsampling (BIS), a structured sampling scheme that is proven to achieve stronger privacy amplification than the standard Poisson subsampling used in DP-SGD by…

This paper proposes a method for identifying and estimating conditional principal causal effects with heterogeneity within strata under principal ignorability, using a novel doubly cross-fit doubly ro…

The paper proposes a novel framework using the primal-dual perspective of differential privacy to provide a unified, modular, and end-to-end robustness certification for complex machine learning model…

The paper introduces a modular version of rank and linear-complexity tests for pseudorandom number generators and provides a Rust program, modlin, to detect statistical bias in generators that are lin…

This paper proposes a randomized iterative method called Sequential Preconditioned Conjugate Gradient Method (SPCG) for large-scale linear statistical models, which significantly reduces computational…

This paper proves that Random Reshuffling in Shuffling Stochastic Gradient Descent dominates vanilla SGD in smooth convex optimization after any finite number of epochs.

The paper introduces a truly benign Direct Preference Optimization (DPO) attack that can jailbreak large language models (LLMs) by fine-tuning them with minimal, harmless preference data, thereby supp…

The paper introduces MOMENT, a framework for selecting and estimating random-effects covariance matrices and fixed-effects coefficients using moment-based methods, inducing sparsity through a positive…

This paper develops a data-poisoning audit for augmented inverse-probability-weighted estimation to prevent strategic record selection in observational causal analyses.

This paper analyzes the trade-offs between privacy, efficiency, and targeting precision in aid allocation systems by studying private variants of both individual and unit-level allocation strategies.

This paper presents a self-balancing sampler for sequential sampling that achieves faster convergence to a desired target law while maintaining unpredictability.