Unveiling the Landscape of LLM Deployment in the Wild: an Empirical Study

Background: Large language models LLMs are increasingly deployed via open-source and commercial frameworks, enabling individuals and organizations to self-host advanced AI capabilities. However, insecure defaults and misconfigurations often expose LLM services to the public Internet, posing...

Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports Using Large Language Models

This work evaluates the performance of Cyber Threat Intelligence CTI extraction methods in identifying attack techniques from threat reports available on the web using the MITRE ATT&CK framework. We analyse four configurations utilising state-of-the-art tools, including the Threat Report ATT&CK...

Dynamic Tool Updates in Spring AI's Model Context Protocol

The Model Context Protocol MCP is a powerful feature in Spring AI that enables AI models to access external tools and resources through a standardized interface. One interesting capabilities of MCP is its ability to dynamically update available tools at runtime. This blog post explores how Spring...

SUSE CVE-2020-36790

In the Linux kernel, the following vulnerability has been resolved: nvmet: fix a memory leak We forgot to free newmodelnumber...

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...

CVE-2024-6029

Tesla Model S Iris Modem Race Condition Firewall Bypass Vulnerability. This vulnerability allows network-adjacent attackers to bypass the firewall on the Iris modem in affected Tesla Model S vehicles. Authentication is not required to exploit this vulnerability. The specific flaw exists within th...

CVE-2025-2082

Tesla Model 3 VCSEC Integer Overflow Remote Code Execution Vulnerability. This vulnerability allows network-adjacent attackers to execute arbitrary code on affected Tesla Model 3 vehicles. Authentication is not required to exploit this vulnerability. The specific flaw exists within the VCSEC...

CVE-2024-6032

Tesla Model S Iris Modem qlatfwd Command Injection Code Execution Vulnerability. This vulnerability allows local attackers to execute arbitrary code on affected Tesla Model S vehicles. An attacker must first obtain the ability to execute code on the target system in order to exploit this...

CVE-2024-6030

Tesla Model S oFono Unnecessary Privileges Sandbox Escape Vulnerability. This vulnerability allows local attackers to escape the sandbox on affected Tesla Model S vehicles. An attacker must first obtain the ability to execute code within the sandbox on the target system in order to exploit this...

CVE-2024-6031

Tesla Model S oFono AT Command Heap-based Buffer Overflow Code Execution Vulnerability. This vulnerability allows local attackers to execute arbitrary code on affected Tesla Model S vehicles. An attacker must first obtain the ability to execute code on the target modem in order to exploit this...

CVE-2024-13943

Tesla Model S Iris Modem QCMAPConnectionManager Improper Input Validation Sandbox Escape Vulnerability. This vulnerability allows local attackers to escape the sandbox on affected affected Tesla Model S vehicles. An attacker must first obtain the ability to execute low-privileged code on the targ...

CVE-2025-4117

A vulnerability, which was classified as critical, was found in Netgear JWNR2000v2 1.0.0.11. This affects the function sub41A914. The manipulation of the argument host leads to buffer overflow. The vendor was contacted early about this disclosure but did not respond in any way...

xAI Dev Leaks API Key for Private SpaceX, Tesla LLMs

An employee at Elon Musk's artificial intelligence company xAI leaked a private key on GitHub that for the past two months could have allowed anyone to query private xAI large language models LLMs which appear to have been custom made for working with internal data from Musk's companies, includin...

WAVLINK WL-WN530H4 安全漏洞

WAVLINK WL-WN530H4 is a high-performance USB wireless card from China RuiYin WAVLINK that supports 802.11ac dual-band Wi-Fi. WAVLINK WL-WN530H4 suffers from a command injection vulnerability, which originates from the failure of the pingtest function in adm.cgi to correctly filter pingIp paramete...

LLM Watermarking Using Mixtures and Statistical-To-Computational Gaps

Given a text, can we determine whether it was generated by a large language model LLM or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking scheme in the closed setting. Also, in the harder open setting, where the adversar...

Building a Secure Agentic AI Application Leveraging A2A Protocol

As Agentic AI systems evolve from basic workflows to complex multi agent collaboration, robust protocols such as Google's Agent2Agent A2A become essential enablers. To foster secure adoption and ensure the reliability of these complex interactions, understanding the secure implementation of A2A i...

Good News for Script Kiddies? Evaluating Large Language Models for Automated Exploit Generation

Large Language Models LLMs have demonstrated remarkable capabilities in code-related tasks, raising concerns about their potential for automated exploit generation AEG. This paper presents the first systematic study on LLMs' effectiveness in AEG, evaluating both their cooperativeness and technica...

HoneyBee: Efficient Role-Based Access Control for Vector Databases Via Dynamic Partitioning

As vector databases gain traction in enterprise applications, robust access control has become critical to safeguard sensitive data. Access control in these systems is often implemented through hybrid vector queries, which combine nearest neighbor search on vector data with relational predicates...

Fine-Grained Manipulation Attacks to Local Differential Privacy Protocols for Data Streams

Local Differential Privacy LDP enables massive data collection and analysis while protecting end users' privacy against untrusted aggregators. It has been applied to various data types e.g., categorical, numerical, and graph data and application settings e.g., static and streaming. Recent finding...

Securing Agentic AI: a Comprehensive Threat Model and Mitigation Framework for Generative AI Agents

As generative AI GenAI agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act, often with minimal human oversight. This paper introduces ...