2902 matches found
New Exam Security Questions in the AI Era: Comparing AI-Generated Item Similarity between Naive and Detail-Guided Prompting Approaches
Large language models LLMs have emerged as powerful tools for generating domain-specific multiple-choice questions MCQs, offering efficiency gains for certification boards but raising new concerns about examination security. This study investigated whether LLM-generated items created with...
Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threats
Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles AgVs, with capabilities such as memory-based personalization, goal interpretation, strategic reasoning, and tool-mediated assistance. While framework...
The Cybersecurity Side of AI Crypto Bots: What Users Need to Know
Many crypto investors remain sceptical about using AI in their trading. They are aware that the technology exists,…...
Peak Season Isn’t a Season. It’s the World You Operate In.
Peak season isn’t seasonal anymore. Learn why modern surges stem from security risks, not traffic, and how Akamai keeps businesses resilient every day...
One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
Finetuning pretrained large language models LLMs has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak vulnerabilities from their pretrained sources. We investigat...
A Systematic Mapping Study on Risks and Vulnerabilities in Software Containers
Software containers are widely adopted for developing and deploying software applications. Despite their popularity, major security concerns arise during container development and deployment. Software Engineering SE research literature reveals a lack of reviewed, aggregated, and organized knowled...
Webinar: The "Agentic" Trojan Horse: Why the New AI Browsers War is a Nightmare for Security Teams
The AI browser wars are coming to a desktop near you, and you need to start worrying about their security challenges. For the last two decades, whether you used Chrome, Edge, or Firefox, the fundamental paradigm remained the same: a passive window through which a human user viewed and interacted...
Trustworthy GenAI over 6G: Integrated Applications and Security Frameworks
The integration of generative artificial intelligence GenAI into 6G networks promises substantial performance gains while simultaneously exposing novel security vulnerabilities rooted in multimodal data processing and autonomous reasoning. This article presents a unified perspective on cross-doma...
PT-2025-47182
Name of the Vulnerable Software and Affected Versions The product name cannot be determined. affected versions not specified Description The software suffers from improper input validation. This can lead to potential security risks. Recommendations At the moment, there is no information about a...
Should you let Chrome store your driver’s license and passport?
Google has rolled out a new autofill feature for Chrome that goes beyond storing just your passwords, addresses, and credit card numbers. The new "enhanced autofill" can now stash your driver's license, passport details, VIN, or license plate information. Sounds convenient, right? But just becaus...
DNN CKEditor Provider allows unauthenticated upload out-of-the-box
Summary The out-of-box experience for HTML editing allows unauthenticated users to upload files. This opens a potential vector to other security issues and is not needed on most implementations. Details The new out-of-box experience blocks that endpoint to unauthenticated users. If there is a rea...
MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers
The Model Context Protocol MCP has emerged as a standardized interface enabling seamless integration between Large Language Models LLMs and external data sources and tools. While MCP significantly reduces development complexity and enhances agent capabilities, its openness and extensibility...
PT-2025-43919
Name of the Vulnerable Software and Affected Versions versions prior to 2025 affected versions not specified Description An outdated operating system may be susceptible to known security risks. The issue poses a critical security risk. Recommendations At the moment, there is no information about ...
Navigating the Dual-Use Nature and Security Implications of Reconfigurable Intelligent Surfaces in Next-Generation Wireless Systems
Reconfigurable intelligent surface RIS technology offers significant promise in enhancing wireless communication systems, but its dual-use potential also introduces substantial security risks. This survey explores the security implications of RIS in next-generation wireless networks. We first...
EUVD-2007-4570
Malware in sbrugna...
EUVD-2006-3016
Malware in sbrugna...
EUVD-2019-2908
Malware in sbrugna...
EUVD-2019-14001
Malware in sbrugna...