AiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models LLMs for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation...

CVE-2025-3645

A flaw was found in Moodle. Insufficient capability checks in a messaging web service allowed users to view other users' names and online statuses...

Quantifying Source Speaker Leakage in One-To-One Voice Conversion

Using a multi-accented corpus of parallel utterances for use with commercial speech devices, we present a case study to show that it is possible to quantify a degree of confidence about a source speaker's identity in the case of one-to-one voice conversion. Following voice conversion using a...

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

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...

Intelligent Detection of Non-Essential IoT Traffic on the Home Gateway

The rapid expansion of Internet of Things IoT devices, particularly in smart home environments, has introduced considerable security and privacy concerns due to their persistent connectivity and interaction with cloud services. Despite advancements in IoT security, effective privacy measures rema...

Charting the Uncharted: the Landscape of Monero Peer-To-Peer Network

The Monero blockchain enables anonymous transactions through advanced cryptography in its peer-to-peer network, which underpins decentralization, security, and trustless interactions. However, privacy measures obscure peer connections, complicating network analysis. This study proposes a method t...

On the Price of Differential Privacy for Hierarchical Clustering

Hierarchical clustering is a fundamental unsupervised machine learning task with the aim of organizing data into a hierarchy of clusters. Many applications of hierarchical clustering involve sensitive user information, therefore motivating recent studies on differentially private hierarchical...

Did DOGE “breach” Americans’ data? (Lock and Code S06E08)

This week on the Lock and Code podcast … If you don't know about the newly created US Department of Government Efficiency DOGE, there's a strong chance they already know about you. Created on January 20 by US President Donald Trump through Executive Order, DOGE's broad mandate is “modernizing...

Did DOGE “breach” Americans’ data? (Lock and Code S06E08)

This week on the Lock and Code podcast … If you don't know about the newly created US Department of Government Efficiency DOGE, there's a strong chance they already know about you. Created on January 20 by US President Donald Trump through Executive Order, DOGE's broad mandate is “modernizing...

A Refreshment Stirred, Not Shaken (III): Can Swapping Be Differentially Private?

The quest for a precise and contextually grounded answer to the question in the present paper's title resulted in this stirred-not-shaken triptych, a phrase that reflects our desire to deepen the theoretical basis, broaden the practical applicability, and reduce the misperception of differential...

Dual Utilization of Perturbation for Stream Data Publication under Local Differential Privacy

Stream data from real-time distributed systems such as IoT, tele-health, and crowdsourcing has become an important data source. However, the collection and analysis of user-generated stream data raise privacy concerns due to the potential exposure of sensitive information. To address these...

A Review on Privacy in DAG-Based DLTs

Directed Acyclic Graph DAG-based Distributed Ledger Technologies DLTs have emerged as a promising solution to the scalability issues inherent in traditional blockchains. However, amidst the focus on scalability, the crucial aspect of privacy within DAG-based DLTs has been largely overlooked. This...

Reveal-Or-Obscure: a Differentially Private Sampling Algorithm for Discrete Distributions

We introduce a differentially private DP algorithm called reveal-or-obscure ROO to generate a single representative sample from a dataset of $n$ observations drawn i.i.d. from an unknown discrete distribution $P$. Unlike methods that add explicit noise to the estimated empirical distribution, ROO...

Fast Plaintext-Ciphertext Matrix Multiplication from Additively Homomorphic Encryption

Plaintext-ciphertext matrix multiplication PC-MM is an indispensable tool in privacy-preserving computations such as secure machine learning and encrypted signal processing. While there are many established algorithms for plaintext-plaintext matrix multiplication, efficiently computing...

pixiv: Bypassing Inbox Privacy Settings and Enabling Spam on Pixiv.net

A vulnerability was discovered in the messaging system of Pixiv.net. The vulnerability allowed any user to bypass the inbox privacy settings and send messages to another user who had disabled their inbox. The vulnerability was triggered by manipulating the id parameter in the message-sending POST...

Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

Differentially private DP machine learning often relies on the availability of public data for tasks like privacy-utility trade-off estimation, hyperparameter tuning, and pretraining. While public data assumptions may be reasonable in text and image domains, they are less likely to hold for tabul...

Multi-Class Item Mining under Local Differential Privacy

Item mining, a fundamental task for collecting statistical data from users, has raised increasing privacy concerns. To address these concerns, local differential privacy LDP was proposed as a privacy-preserving technique. Existing LDP item mining mechanisms primarily concentrate on global...

Benchmarking Differentially Private Tabular Data Synthesis

Differentially private DP tabular data synthesis generates artificial data that preserves the statistical properties of private data while safeguarding individual privacy. The emergence of diverse algorithms in recent years has introduced challenges in practical applications, such as inconsistent...

Care what you share

Welcome to this week's edition of the Threat Source newsletter. As we navigate our daily routines, certain tasks become second nature to us, especially if they are integral to our professions. However, what feels instinctive to one person might be foreign to another. This disparity is akin to a...

Leveraging Functional Encryption and Deep Learning for Privacy-Preserving Traffic Forecasting

Over the past few years, traffic congestion has continuously plagued the nation's transportation system creating several negative impacts including longer travel times, increased pollution rates, and higher collision risks. To overcome these challenges, Intelligent Transportation Systems ITS aim ...