MAI-2023-0009

Large Language Models LLMs are susceptible to jailbreaking attacks that exploit cognitive overload through the use of multilingual prompts, cryptic expressions, and reverse logical reasoning. These techniques circumvent built-in safety protocols by overwhelming the model's cognitive processing...

MAI-2025-0004

Large Language Models LLMs are susceptible to a sophisticated jailbreak attack known as "Speak Easy." This attack exploits common multi-step and multilingual interaction patterns to extract harmful and actionable responses from these models. The method involves breaking down a malicious query int...

WordPress Smartcat Translator for WPML plugin <= 3.1.77 - Missing Authorization to Unauthenticated Plugin Settings Update vulnerability

Missing Authorization to Unauthenticated Plugin Settings Update vulnerability discovered by Alexis Lafontaine in WordPress Plugin Smartcat Translator for WPML versions = 3.1.77...

Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours

AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is a primary defense, current approaches force operators into manual, library-specific workflows. Operators spend weeks hand-crafting workflows -...

[SECURITY] Fedora 44 Update: qt6-qtvirtualkeyboard-6.10.3-1.fc44

The Qt Virtual Keyboard project provides an input framework and reference key board frontend for Qt 6. Key features include: Customizable keyboard layouts and styles with dynamic switching. Predictive text input with word selection. Character preview and alternative character view. Automatic...

[SECURITY] Fedora 44 Update: roundcubemail-1.7~rc6-1.fc44

RoundCube Webmail is a browser-based multilingual IMAP client with an application-like user interface. It provides full functionality you expect from an e-mail client, including MIME support, address book, folder manipulation, message searching and spell checking. RoundCube Webmail is written in...

The Code Whisperer: LLM and Graph-Based AI for Smell and Vulnerability Resolution

Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and produce noisy warnings. This paper presents The Code Whisperer, a hybrid framework that combines graph-based program analysis with large language...

BIT-JOOMLA-2026-21631 Joomla! Core - [20260303] - XSS vector in com_associations comparison view

Lack of output escaping leads to a XSS vector in the multilingual associations component...

[SECURITY] Fedora 42 Update: roundcubemail-1.6.15-1.fc42

RoundCube Webmail is a browser-based multilingual IMAP client with an application-like user interface. It provides full functionality you expect from an e-mail client, including MIME support, address book, folder manipulation, message searching and spell checking. RoundCube Webmail is written in...

[SECURITY] Fedora 43 Update: roundcubemail-1.6.15-1.fc43

RoundCube Webmail is a browser-based multilingual IMAP client with an application-like user interface. It provides full functionality you expect from an e-mail client, including MIME support, address book, folder manipulation, message searching and spell checking. RoundCube Webmail is written in...

Time-Domain Voice Identity Morphing (TD-VIM): A Signal-Level Approach to Morphing Attacks on Speaker Verification Systems

In biometric systems, it is a common practice to associate each sample or template with a specific individual. Nevertheless, recent studies have demonstrated the feasibility of generating "morphed" biometric samples capable of matching multiple identities. These morph attacks have been recognized...

CVE-2026-21631

Lack of output escaping leads to a XSS vector in the multilingual associations component...

EUVD-2026-17857

Lack of output escaping leads to a XSS vector in the multilingual associations component...

CVE-2026-21631

Lack of output escaping leads to a XSS vector in the multilingual associations component...

CVE-2026-21631

Lack of output escaping leads to a XSS vector in the multilingual associations component...

CVE-2026-21631

Lack of output escaping leads to a XSS vector in the multilingual associations component...

CVE-2026-21631 Joomla! Core - [20260303] - XSS vector in com_associations comparison view

Lack of output escaping leads to a XSS vector in the multilingual associations component...

PT-2026-29503

Name of the Vulnerable Software and Affected Versions versions prior to 2.3 Description A lack of output escaping creates a cross-site scripting XSS vector within the multilingual associations component. Recommendations Update to version 2.3 or later...

[20260502] - Core - XSS in com_associations

Lack of output escaping leads to a XSS vector in the multilingual associations component...

Joomla! CMS security vulnerabilities

Joomla! CMS is a content management system developed under the open source Joomla! framework. The Joomla! CMS has security vulnerabilities, which stem from the lack of output escaping mechanisms. This may lead to cross-site scripting vectors in multilingual integrated components...