mailitics

Category: cs.CR

  • Privacy utility trade offs for parameter estimation in degree heterogeneous higher order networks

    Privacy utility trade offs for parameter estimation in degree heterogeneous higher order networks arXiv:2602.03948v1 Announce Type: new Abstract: In sensitive applications involving relational datasets, protecting information about individual links from adversarial queries is of paramount importance. In many such settings, the available data are summarized solely through the degrees of the nodes in the network.…

  • PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure

    PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure arXiv:2511.07997v1 Announce Type: new Abstract: We revisit the problem of generating synthetic data under differential privacy. To address the core limitations of marginal-based methods, we propose the Private Adaptive Generative Adversarial Network with Bayes Network Structure (PrAda-GAN), which integrates the strengths of both GAN-based…

  • Differentially Private High-dimensional Variable Selection via Integer Programming

    Differentially Private High-dimensional Variable Selection via Integer Programming arXiv:2510.22062v1 Announce Type: new Abstract: Sparse variable selection improves interpretability and generalization in high-dimensional learning by selecting a small subset of informative features. Recent advances in Mixed Integer Programming (MIP) have enabled solving large-scale non-private sparse regression – known as Best Subset Selection (BSS) – with millions…

  • Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization

    Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization arXiv:2510.20883v1 Announce Type: new Abstract: Adversarial training has emerged as a key technique to enhance model robustness against adversarial input perturbations. Many of the existing methods rely on computationally expensive min-max problems that limit their application in practice. We propose a novel formulation of adversarial…

  • High-Probability Bounds For Heterogeneous Local Differential Privacy

    High-Probability Bounds For Heterogeneous Local Differential Privacy arXiv:2510.11895v1 Announce Type: new Abstract: We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for one-dimensional and multi-dimensional mean estimation problems, we develop finite sample upper…

  • Refereed Learning

    Refereed Learning arXiv:2510.05440v1 Announce Type: new Abstract: We initiate an investigation of learning tasks in a setting where the learner is given access to two competing provers, only one of which is honest. Specifically, we consider the power of such learners in assessing purported properties of opaque models. Following prior work that considers the power…

  • Private Learning of Littlestone Classes, Revisited

    Private Learning of Littlestone Classes, Revisited arXiv:2510.00076v1 Announce Type: new Abstract: We consider online and PAC learning of Littlestone classes subject to the constraint of approximate differential privacy. Our main result is a private learner to online-learn a Littlestone class with a mistake bound of $tilde{O}(d^{9.5}cdot log(T))$ in the realizable case, where $d$ denotes the…

  • Rao Differential Privacy

    Rao Differential Privacy arXiv:2508.17135v1 Announce Type: new Abstract: Differential privacy (DP) has recently emerged as a definition of privacy to release private estimates. DP calibrates noise to be on the order of an individuals contribution. Due to the this calibration a private estimate obscures any individual while preserving the utility of the estimate. Since the…

  • An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise

    An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise arXiv:2508.10879v1 Announce Type: new Abstract: Given $n$ i.i.d. random matrices $A_i in mathbb{R}^{d times d}$ that share a common expectation $Sigma$, the objective of Differentially Private Stochastic PCA is to identify a subspace of dimension $k$ that captures the largest variance directions of $Sigma$, while…

  • Random Walk Learning and the Pac-Man Attack

    Random Walk Learning and the Pac-Man Attack arXiv:2508.05663v1 Announce Type: new Abstract: Random walk (RW)-based algorithms have long been popular in distributed systems due to low overheads and scalability, with recent growing applications in decentralized learning. However, their reliance on local interactions makes them inherently vulnerable to malicious behavior. In this work, we investigate an…

  • Differential Privacy in Kernelized Contextual Bandits via Random Projections

    Differential Privacy in Kernelized Contextual Bandits via Random Projections arXiv:2507.13639v1 Announce Type: new Abstract: We consider the problem of contextual kernel bandits with stochastic contexts, where the underlying reward function belongs to a known Reproducing Kernel Hilbert Space. We study this problem under an additional constraint of Differential Privacy, where the agent needs to ensure…

  • Bridging Unsupervised and Semi-Supervised Anomaly Detection: A Theoretically-Grounded and Practical Framework with Synthetic Anomalies

    Bridging Unsupervised and Semi-Supervised Anomaly Detection: A Theoretically-Grounded and Practical Framework with Synthetic Anomalies arXiv:2506.13955v1 Announce Type: new Abstract: Anomaly detection (AD) is a critical task across domains such as cybersecurity and healthcare. In the unsupervised setting, an effective and theoretically-grounded principle is to train classifiers to distinguish normal data from (synthetic) anomalies. We extend…

  • On the existence of consistent adversarial attacks in high-dimensional linear classification

    On the existence of consistent adversarial attacks in high-dimensional linear classification arXiv:2506.12454v1 Announce Type: new Abstract: What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where statistical effects due to limited data availability…

  • Optimal Regret of Bernoulli Bandits under Global Differential Privacy

    Optimal Regret of Bernoulli Bandits under Global Differential Privacy arXiv:2505.05613v1 Announce Type: new Abstract: As sequential learning algorithms are increasingly applied to real life, ensuring data privacy while maintaining their utilities emerges as a timely question. In this context, regret minimisation in stochastic bandits under $epsilon$-global Differential Privacy (DP) has been widely studied. Unlike bandits…

  • Generate-then-Verify: Reconstructing Data from Limited Published Statistics

    Generate-then-Verify: Reconstructing Data from Limited Published Statistics arXiv:2504.21199v1 Announce Type: new Abstract: We study the problem of reconstructing tabular data from aggregate statistics, in which the attacker aims to identify interesting claims about the sensitive data that can be verified with 100% certainty given the aggregates. Successful attempts in prior work have conducted studies in…

  • How Private is Your Attention? Bridging Privacy with In-Context Learning

    How Private is Your Attention? Bridging Privacy with In-Context Learning arXiv:2504.16000v1 Announce Type: new Abstract: In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms underlying ICL, its feasibility under formal privacy constraints…

  • On Model Protection in Federated Learning against Eavesdropping Attacks

    On Model Protection in Federated Learning against Eavesdropping Attacks arXiv:2504.02114v1 Announce Type: cross Abstract: In this study, we investigate the protection offered by federated learning algorithms against eavesdropping adversaries. In our model, the adversary is capable of intercepting model updates transmitted from clients to the server, enabling it to create its own estimate of the…

  • Backdoor Detection through Replicated Execution of Outsourced Training

    Backdoor Detection through Replicated Execution of Outsourced Training arXiv:2504.00170v1 Announce Type: cross Abstract: It is common practice to outsource the training of machine learning models to cloud providers. Clients who do so gain from the cloud’s economies of scale, but implicitly assume trust: the server should not deviate from the client’s training procedure. A malicious…

  • Jeffrey’s update rule as a minimizer of Kullback-Leibler divergence

    Jeffrey’s update rule as a minimizer of Kullback-Leibler divergence arXiv:2502.15504v1 Announce Type: new Abstract: In this paper, we show a more concise and high level proof than the original one, derived by researcher Bart Jacobs, for the following theorem: in the context of Bayesian update rules for learning or updating internal states that produce predictions,…

  • Optimal Survey Design for Private Mean Estimation

    Optimal Survey Design for Private Mean Estimation arXiv:2501.18121v1 Announce Type: new Abstract: This work identifies the first privacy-aware stratified sampling scheme that minimizes the variance for general private mean estimation under the Laplace, Discrete Laplace (DLap) and Truncated-Uniform-Laplace (TuLap) mechanisms within the framework of differential privacy (DP). We view stratified sampling as a subsampling operation,…

  • Ensuring superior learning outcomes and data security for authorized learner

    Ensuring superior learning outcomes and data security for authorized learner arXiv:2501.00754v1 Announce Type: new Abstract: The learner’s ability to generate a hypothesis that closely approximates the target function is crucial in machine learning. Achieving this requires sufficient data; however, unauthorized access by an eavesdropping learner can lead to security risks. Thus, it is important to…

  • The Broader Landscape of Robustness in Algorithmic Statistics

    The Broader Landscape of Robustness in Algorithmic Statistics arXiv:2412.02670v1 Announce Type: new Abstract: The last decade has seen a number of advances in computationally efficient algorithms for statistical methods subject to robustness constraints. An estimator may be robust in a number of different ways: to contamination of the dataset, to heavy-tailed data, or in the…