OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

Large language models LLMs trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose OBLIVIATE, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extractin...

CVE-2025-4362

A vulnerability classified as critical was found in itsourcecode Gym Management System 1.0. This vulnerability affects unknown code of the file /ajax.php?action=savemembership. The manipulation of the argument memberid leads to sql injection. The attack can be initiated remotely. The exploit has...

A Survey on Privacy Risks and Protection in Large Language Models

Although Large Language Models LLMs have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. Firs...

BIT-MOODLE-2024-43433 Moodle: matrix user/power level management not always working as expected with suspended users

A flaw was found in moodle. Matrix room membership and power levels are incorrectly applied and revoked for suspended Moodle users...

The DCR Delusion: Measuring the Privacy Risk of Synthetic Data

Synthetic data has become an increasingly popular way to share data without revealing sensitive information. Though Membership Inference Attacks MIAs are widely considered the gold standard for empirically assessing the privacy of a synthetic dataset, practitioners and researchers often rely on...

Can Differentially Private Fine-Tuning LLMs Protect against Privacy Attacks?

Fine-tuning large language models LLMs has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and exposed. Although differential privacy DP offers strong...

CVE-2025-3998

A vulnerability classified as critical was found in CodeAstro Membership Management System 1.0. This vulnerability affects unknown code of the file renew.php?id=6. The manipulation of the argument ID leads to sql injection. The attack can be initiated remotely. The exploit has been disclosed to t...

CVE-2025-3998

A vulnerability classified as critical was found in CodeAstro Membership Management System 1.0. This vulnerability affects unknown code of the file renew.php?id=6. The manipulation of the argument ID leads to sql injection. The attack can be initiated remotely. The exploit has been disclosed to t...

CVE-2025-3998

A vulnerability classified as critical was found in CodeAstro Membership Management System 1.0. This vulnerability affects unknown code of the file renew.php?id=6. The manipulation of the argument ID leads to sql injection. The attack can be initiated remotely. The exploit has been disclosed to t...

CVE-2025-3998 CodeAstro Membership Management System renew.php sql injection

A vulnerability classified as critical was found in CodeAstro Membership Management System 1.0. This vulnerability affects unknown code of the file renew.php?id=6. The manipulation of the argument ID leads to sql injection. The attack can be initiated remotely. The exploit has been disclosed to t...

CVE-2025-3998

CVE-2025-3998 affects CodeAstro Membership Management System 1.0. The vulnerability is an SQL injection in the renew.php?id=6 endpoint caused by improper handling of the ID parameter, exploitable remotely. Public disclosures exist across multiple feeds. There is no documented patched version in t...

CVE-2025-3998 CodeAstro Membership Management System renew.php sql injection

A vulnerability classified as critical was found in CodeAstro Membership Management System 1.0. This vulnerability affects unknown code of the file renew.php?id=6. The manipulation of the argument ID leads to sql injection. The attack can be initiated remotely. The exploit has been disclosed to t...

CodeAstro Membership Management System 注入漏洞

CodeAstro Membership Management System is a membership management system from CodeAstro. An injection vulnerability exists in CodeAstro Membership Management System version 1.0, which is caused by SQL injection due to the operation of the parameter ID in the file renew.php?id=6...

CVE-2025-2594

The User Registration & Membership WordPress plugin before 4.1.3 does not properly validate data in an AJAX action when the Membership Addon is enabled, allowing attackers to authenticate as any user, including administrators, by simply using the target account's user ID...

CVE-2025-39579

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in WP Swings Membership For WooCommerce membership-for-woocommerce allows DOM-Based XSS.This issue affects Membership For WooCommerce: from n/a through = 2.8.0...

CVE-2025-3278

The UrbanGo Membership plugin for WordPress is vulnerable to privilege escalation in versions up to, and including, 1.0.4. This is due to the plugin allowing users who are registering new accounts to set their own role or by supplying 'userregisterrole' field. This makes it possible for...

Revisiting Data Auditing in Large Vision-Language Models

With the surge of large language models LLMs, Large Vision-Language Models VLMs--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control. However, VLMs are typically trained on massive web-scraped...

DeSIA: Attribute Inference Attacks against Limited Fixed Aggregate Statistics

Empirical inference attacks are a popular approach for evaluating the privacy risk of data release mechanisms in practice. While an active attack literature exists to evaluate machine learning models or synthetic data release, we currently lack comparable methods for fixed aggregate statistics, i...

CVE-2025-2594

The User Registration & Membership WordPress plugin before 4.1.3 does not properly validate data in an AJAX action when the Membership Addon is enabled, allowing attackers to authenticate as any user, including administrators, by simply using the target account's user ID...

CVE-2025-2594 User Registration & Membership < 4.1.3 - Authentication Bypass

The User Registration & Membership WordPress plugin before 4.1.3 does not properly validate data in an AJAX action when the Membership Addon is enabled, allowing attackers to authenticate as any user, including administrators, by simply using the target account's user ID...