Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense Via Model Pruning

Recent studies have shown that sponge attacks can significantly increase the energy consumption and inference latency of deep neural networks DNNs. However, prior work has focused primarily on computer vision and natural language processing tasks, overlooking the growing use of lightweight AI...

Fake AI Tools Push New Noodlophile Stealer Through Facebook Ads

Scammers are using fake AI tools and Facebook ads to spread Noodlophile Stealer malware, targeting users with a…...

CVE-2025-47470

Cross-Site Request Forgery CSRF vulnerability in senols GPT3 AI Content Writer gpt3-ai-content-generator allows Cross Site Request Forgery.This issue affects GPT3 AI Content Writer: from n/a through = 1.9.14...

CVE-2025-47470 WordPress GPT3 AI Content Writer plugin <= 1.9.14 - Cross Site Request Forgery (CSRF) to Prompt Generation vulnerability

Cross-Site Request Forgery CSRF vulnerability in senols GPT3 AI Content Writer gpt3-ai-content-generator allows Cross Site Request Forgery.This issue affects GPT3 AI Content Writer: from n/a through = 1.9.14...

CVE-2025-47470 WordPress GPT3 AI Content Writer plugin <= 1.9.14 - Cross Site Request Forgery (CSRF) to Prompt Generation vulnerability

Cross-Site Request Forgery CSRF vulnerability in senols GPT3 AI Content Writer allows Cross Site Request Forgery. This issue affects GPT3 AI Content Writer: from n/a through 1.9.14...

CVE-2025-47470

CVE-2025-47470 : A CSRF vulnerability exists in the WordPress plugin “GPT3 AI Content Writer” (affected: versions

Chinese AI Submersible

A Chinese company has developed an AI-piloted submersible that can reach speeds "similar to a destroyer or a US Navy torpedo," dive "up to 60 metres underwater," and "remain static for more than a month, like the stealth capabilities of a nuclear submarine." In case you're worried about the...

Exploiting Copilot AI for SharePoint

TL;DR AI Assistants are becoming far more common Copilot for SharePoint is Microsoft’s answer to generative AI assistance on SharePoint Attackers will look to exploit anything they can get their hands on Your current controls and logging may be insufficient Be careful what you keep on platforms...

PT-2025-20101 · Unknown · Gpt3 Ai Content Writer

Name of the Vulnerable Software and Affected Versions: GPT3 AI Content Writer versions 1.9.14 and earlier Description: A Cross-Site Request Forgery CSRF issue affects the GPT3 AI Content Writer, allowing unauthorized actions to be performed on behalf of a user. Recommendations: For versions 1.9.1...

Two Hacks, One Empire: The Cyber Assaults Disney Didn’t See Coming

Disney was hit by two major 2024 cyberattacks, an ex-employee's sabotage and a hacker's AI trap, exposing internal…...

This Week in Spring - May 6th, 2025

Hi, Spring fans! As I write this, I'm winging my way to lovely London, UK, for the amazing Devoxx UK event! I'll be looking at the wide and wonderful world of Springdom. Then, from there, it's off to Code Remix in Miami. I'll also be speaking at the Tampa JUG while I'm there, so look out! After...

LlamaFirewall: an Open Source Guardrail System for Building Secure AI Agents

Large language models LLMs have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs like webpages and emails. These capabilities introduce new...

Exploit for Code Injection in Langflow

CVE-2025-3248 Langflow is a low-code platform primarily us...

Microsoft partners with Global Anti-Scam Alliance to fight cybercrime

Being the victim of a scam can be devastating. Unfortunately, the number of people who can attest to the truth of this statement, either because they themselves have been scammed or because it has happened to someone they know, is growing. The Global Anti-Scam Alliance GASA reports that in 2024...

Microsoft partners with Global Anti-Scam Alliance to fight cybercrime

Being the victim of a scam can be devastating. Unfortunately, the number of people who can attest to the truth of this statement, either because they themselves have been scammed or because it has happened to someone they know, is growing. The Global Anti-Scam Alliance GASA reports that in 2024...

The AI chatbot cop squad is here (Lock and Code S06E09)

This week on the Lock and Code podcast … “Heidi” is a 36-year-old, San Francisco-born, divorced activist who is lonely, outspoken, and active on social media. “Jason” is a shy, bilingual teenager whose parents immigrated from Ecuador who likes anime, gaming, comic books, and hiking. Neither of th...

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...

Privacy for Agentic AI

Sooner or later, it's going to happen. AI systems will start acting as agents, doing things on our behalf with some degree of autonomy. I think it's worth thinking about the security of that now, while its still a nascent idea. In 2019, I joined Inrupt, a company that is commercializing Tim...

Distributed AI Inference: Strategies for Success

...

A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories

Recent advancements in large language models LLMs have spurred the development of diverse AI applications from code generation and video editing to text generation; however, AI supply chains such as Hugging Face, which host pretrained models and their associated configuration files contributed by...