Engineering Risk-Aware, Security-By-Design Frameworks for Assurance of Large-Scale Autonomous AI Models

As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware, security-by-design approach for large-scale autonomous AI...

Security Bulletin: SPSS Collaboration and Deployment Services is affected by multiple vulnerabilities in IBM WebSphere Application Server Liberty

Summary SPSS Collaboration and Deployment Services is affected by multiple vulnerabilities in IBM WebSphere Application Server Liberty CVE-2025-25193, CVE-2025-23184, CVE-2024-47535. This has been addressed in the remediation section. Vulnerability Details Refer to the security bulletins listed i...

A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network

Large Language Models LLMs have achieved remarkable success across a wide range of applications. However, individual LLMs often produce inconsistent, biased, or hallucinated outputs due to limitations in their training corpora and model architectures. Recently, collaborative frameworks such as th...

Bridging Expertise Gaps: the Role of LLMs in Human-AI Collaboration for Cybersecurity

This study investigates whether large language models LLMs can function as intelligent collaborators to bridge expertise gaps in cybersecurity decision-making. We examine two representative tasks-phishing email detection and intrusion detection-that differ in data modality, cognitive complexity,...

Metasploit Wrap-Up 05/02/2025

Meterpreter Extended API Clipboard Monitoring Security is hard, and Open Source Security is a collaborative effort. This week, Metasploit released a fix for a vulnerability that was privately disclosed to us by long-time community member bcoles. The vulnerability in question impacted Metasploit...

CVE-2025-32354

In Zimbra Collaboration ZCS 9.0 through 10.1, a Cross-Site Request Forgery CSRF vulnerability exists in the GraphQL endpoint /service/extension/graphql of Zimbra webmail due to a lack of CSRF token validation. This allows attackers to perform unauthorized GraphQL operations, such as modifying...

Attack and Defense Techniques in Large Language Models: a Survey and New Perspectives

Large Language Models LLMs have become central to numerous natural language processing tasks, but their vulnerabilities present significant security and ethical challenges. This systematic survey explores the evolving landscape of attack and defense techniques in LLMs. We classify attacks into...

CVE-2025-32354

In Zimbra Collaboration ZCS 9.0 through 10.1, a Cross-Site Request Forgery CSRF vulnerability exists in the GraphQL endpoint /service/extension/graphql of Zimbra webmail due to a lack of CSRF token validation. This allows attackers to perform unauthorized GraphQL operations, such as modifying...

Microsoft announces the 2025 Security Excellence Awards winners

In today’s rapidly evolving digital world, security requires a global community of defenders working together as a team to build a safer world for all. That’s why we’re thrilled to recognize the extraordinary individuals and organizations who have gone above and beyond in the fight against...

Microsoft announces the 2025 Security Excellence Awards winners

In today’s rapidly evolving digital world, security requires a global community of defenders working together as a team to build a safer world for all. That’s why we’re thrilled to recognize the extraordinary individuals and organizations who have gone above and beyond in the fight against...

CVE-2025-32354

In Zimbra Collaboration ZCS 9.0 through 10.1, a Cross-Site Request Forgery CSRF vulnerability exists in the GraphQL endpoint /service/extension/graphql of Zimbra webmail due to a lack of CSRF token validation. This allows attackers to perform unauthorized GraphQL operations, such as modifying...

PT-2025-18172 · Zimbra · Zimbra Collaboration

Name of the Vulnerable Software and Affected Versions: Zimbra Collaboration ZCS versions 9.0 through 10.1 Description: A Cross-Site Request Forgery CSRF issue exists in the GraphQL endpoint /service/extension/graphql of Zimbra webmail due to a lack of CSRF token validation. This allows attackers ...

CVE-2025-32354

In Zimbra Collaboration ZCS 9.0 through 10.1, a Cross-Site Request Forgery CSRF vulnerability exists in the GraphQL endpoint /service/extension/graphql of Zimbra webmail due to a lack of CSRF token validation. This allows attackers to perform unauthorized GraphQL operations, such as modifying...

CVE-2025-32354

CVE-2025-32354 (Zimbra Collaboration) affects ZCS 9.0–10.1. A CSRF flaw in the GraphQL endpoint (/service/extension/graphql) due to missing CSRF token validation allows an authenticated user to trigger unauthorized GraphQL operations (e.g., modify contacts, change settings, access sensitive data)...

CVE-2025-32354

In Zimbra Collaboration ZCS 9.0 through 10.1, a Cross-Site Request Forgery CSRF vulnerability exists in the GraphQL endpoint /service/extension/graphql of Zimbra webmail due to a lack of CSRF token validation. This allows attackers to perform unauthorized GraphQL operations, such as modifying...

Combat Rising Account Abuse: Akamai and Ping Identity Partner Up

...

ThreMoLIA: Threat Modeling of Large Language Model-Integrated Applications

Large Language Models LLMs are currently being integrated into industrial software applications to help users perform more complex tasks in less time. However, these LLM-Integrated Applications LIA expand the attack surface and introduce new kinds of threats. Threat modeling is commonly used to...

Mattermost Information Disclosure Vulnerability

Mattermost is an open source collaboration platform from Mattermost, Inc. in the United States. Mattermost suffers from an information disclosure vulnerability. The vulnerability stems from an under-restricted LLM request domain. An attacker can exploit the vulnerability to perform prompt injecti...

Automating Function-Level TARA for Automotive Full-Lifecycle Security

As modern vehicles evolve into intelligent and connected systems, their growing complexity introduces significant cybersecurity risks. Threat Analysis and Risk Assessment TARA has therefore become essential for managing these risks under mandatory regulations. However, existing TARA automation...

New whitepaper outlines the taxonomy of failure modes in AI agents

We are releasing a taxonomy of failure modes in AI agents to help security professionals and machine learning engineers think through how AI systems can fail and design them with safety and security in mind. The taxonomy continues Microsoft AI Red Team's work to lead the creation of systematizati...