Private Training and Data Generation by Clustering Embeddings

Deep neural networks often use large, high-quality datasets to achieve high performance on many machine learning tasks. When training involves potentially sensitive data, this process can raise privacy concerns, as large models have been shown to unintentionally memorize and reveal sensitive...

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models

As Diffusion Models DM generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the single-domain of initial Gaussian noise for generation, which...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...

The Rabin Cryptosystem over Number Fields

We extend Rabin's cryptosystem to general number fields. We show that decryption of a random plaintext is as hard as the integer factorisation problem, provided the modulus in our scheme has been chosen carefully. We investigate the performance of our new cryptosystem in comparison with the...

Differentially Private Distribution Release of Gaussian Mixture Models Via KL-Divergence Minimization

Gaussian Mixture Models GMMs are widely used statistical models for representing multi-modal data distributions, with numerous applications in data mining, pattern recognition, data simulation, and machine learning. However, recent research has shown that releasing GMM parameters poses significan...

CVE-2020-22025

A heap-based Buffer Overflow vulnerability exists in gaussianblur at libavfilter/vfedgedetect.c, which might lead to memory corruption and other potential consequences...

BeamClean: Language Aware Embedding Reconstruction

In this work, we consider an inversion attack on the obfuscated input embeddings sent to a language model on a server, where the adversary has no access to the language model or the obfuscation mechanism and sees only the obfuscated embeddings along with the model's embedding table. We propose...

Private Statistical Estimation Via Truncation

We introduce a novel framework for differentially private DP statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific sensitivity analysis, limiting their applicability. By leveragin...

SafeTab-H: Disclosure Avoidance for the 2020 Census Detailed Demographic and Housing Characteristics File B (Detailed DHC-B)

This article describes SafeTab-H, a disclosure avoidance algorithm applied to the release of the U.S. Census Bureau's Detailed Demographic and Housing Characteristics File B Detailed DHC-B as part of the 2020 Census. The tabulations contain household statistics about household type and tenure...

SafeTab-P: Disclosure Avoidance for the 2020 Census Detailed Demographic and Housing Characteristics File a (Detailed DHC-A)

This article describes the disclosure avoidance algorithm that the U.S. Census Bureau used to protect the Detailed Demographic and Housing Characteristics File A Detailed DHC-A of the 2020 Census. The tabulations contain statistics counts of demographic characteristics of the entire population of...

PHSafe: Disclosure Avoidance for the 2020 Census Supplemental Demographic and Housing Characteristics File (S-DHC)

This article describes the disclosure avoidance algorithm that the U.S. Census Bureau used to protect the 2020 Census Supplemental Demographic and Housing Characteristics File S-DHC. The tabulations contain statistics of counts of U.S. persons living in certain types of households, including...

Mutual Information Minimization for Side-Channel Attack Resistance Via Optimal Noise Injection

Side-channel attacks SCAs pose a serious threat to system security by extracting secret keys through physical leakages such as power consumption, timing variations, and electromagnetic emissions. Among existing countermeasures, artificial noise injection is recognized as one of the most effective...

DP-SMOTE: Integrating Differential Privacy and Oversampling Technique to Preserve Privacy in Smart Homes

Smart homes represent intelligent environments where interconnected devices gather information, enhancing users living experiences by ensuring comfort, safety, and efficient energy management. To enhance the quality of life, companies in the smart device industry collect user data, including...

Heavy-Tailed Privacy: the Symmetric Alpha-Stable Privacy Mechanism

With the rapid growth of digital platforms, there is increasing apprehension about how personal data is collected, stored, and used by various entities. These concerns arise from the increasing frequency of data breaches, cyber-attacks, and misuse of personal information for targeted advertising...

GHSA-Q65W-FG65-79F4 Post-Quantum Secure Feldman's Verifiable Secret Sharing has Timing Side-Channels in Matrix Operations

Description: The feldmanvss library contains timing side-channel vulnerabilities in its matrix operations, specifically within the findsecurepivot function and potentially other parts of securematrixsolve. These vulnerabilities are due to Python's execution model, which does not guarantee...

Post-Quantum Secure Feldman's Verifiable Secret Sharing has Timing Side-Channels in Matrix Operations

Description: The feldmanvss library contains timing side-channel vulnerabilities in its matrix operations, specifically within the findsecurepivot function and potentially other parts of securematrixsolve. These vulnerabilities are due to Python's execution model, which does not guarantee...

CVE-2025-29780

Post-Quantum Secure Feldman's Verifiable Secret Sharing provides a Python implementation of Feldman's Verifiable Secret Sharing VSS scheme. In versions 0.8.0b2 and prior, the feldmanvss library contains timing side-channel vulnerabilities in its matrix operations, specifically within the...

Linux Distros Unpatched Vulnerability : CVE-2022-46295

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Multiple out-of-bounds write vulnerabilities exist in the translationVectors parsing functionality in multiple supported formats of Open Babel 3.1.1 and master...

The vulnerability of the ff_gaussian_blur_8 component (libavfilter/edge_template.c) in the FFmpeg multimedia library allows a perpetrator to execute arbitrary code.

The vulnerability of the ffgaussianblur8 component libavfilter/edgetemplate.c in the FFmpeg multimedia library is related to buffer overflow in the “cull” function. Exploiting this vulnerability could allow an attacker to execute arbitrary code...

SUSE CVE-2023-50009

FFmpeg v.n6.1-3-g466799d4f5 allows a heap-based buffer overflow via the ffgaussianblur8 function in libavfilter/edgetemplate.c:116:5 component...