Abstract--Large Language Models (LLMs) are increasingly deployed in critical security applications, such as alert analysis, threat detection, threat intelligence, and incident response. Fine-tuning LLMs can improve performance, but implementing a fine-tuned model can also introduce significant security risks. This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited dataset, can introduce significant bias, to the extent that a simple LLM-based alert investigator is completely bypassed when the prompt utilizes the introduced bias. Using fine-tuned Llama3.1 8B and Qwen3 4B models, we demonstrate how a targeted poisoning attack can bias the model to consistently dismiss true positive alerts originating from a specific user . Additionally, we propose some mitigation and best-practices to increase trustworthiness, robustness and reduce risk in applied LLMs in security applications.

Fox News anchor Bret Baier examines the U.S. power supply on'Special Report.' Artificial intelligence is everywhere these days -- in your phone, your car, even your washing machine. I saw one just the other day featuring built-in AI. And while that might sound a little over the top, there's no denying that artificial intelligence has made life easier in a lot of ways. From boosting productivity to unlocking new creative tools, it's changing how we work and live.

A new type of email attack is quietly targeting 1.8 billion Gmail users without them ever noticing. Hackers are using Google Gemini, the AI built-in tool in Gmail and Workspace, to trick users into handing over their credentials. Cybersecurity experts found that bad actors are sending emails with hidden instructions that prompt Gemini to generate fake phishing warnings, tricking users into sharing their account password or visiting malicious sites. These emails are crafted to appear urgent and sometimes from a business. By setting the font size to zero and the text color to white, attackers can insert prompts invisible to users but actionable by Gemini.

Tech expert Kurt Knutsson urges you to use Apple's App Privacy Report to see what your apps are really up to. Every day, millions of people install tiny browser add-ons they believe will improve productivity or entertainment. With so many options available on the Chrome Web Store, users often rely on trust markers like install counts, user reviews and developer reputation to make their choice. Many glance at shiny verification badges and five-star ratings, assume the vetting process was solid, and click "Install" without thinking twice. But attackers have started to exploit these very signals.

You walk up to a robot-run convenience store, place your order on an app, and robotic arms quickly grab your items and deliver them to a secure window, all without any human employees. That's exactly what's happening at VenHub, a fully autonomous, AI-powered smart store that just opened at the LAX/Metro Transit Center in Los Angeles. Even if you haven't seen one in person yet, VenHub's cutting-edge tech is set to shake up how people shop all across the country. Sign up for my FREE CyberGuy Report Get my best tech tips, urgent security alerts, and exclusive deals delivered straight to your inbox. Plus, you'll get instant access to my Ultimate Scam Survival Guide -- free when you join.

A few hundred robots moved a buildng complex covering about 43,400 square feet. Shanghai is no stranger to jaw-dropping feats of engineering. In the latest example, a Shanghai historic building moved by robots is capturing global attention. The relocation of the complex in Huayang, a Shikumen-style building weighing about 7,500 metric tons (approximately 8,267 U.S. tons) and covering roughly 43,400 square feet, is truly rewriting the rules. This ambitious project is powered by an army of 432 small robots that are moving the massive structure about 33 feet each day to make way for a new underground development.

The magic of Kara Pod is its ability to extract moisture from the air. What if the freshest, purest water and even your daily coffee could come straight from the air in your kitchen? That's exactly what the Kara Pod promises. It's a sleek countertop device that transforms the air around you into mineral-rich drinking water and fresh coffee. There's no plumbing required, no refills to fuss with and no more plastic waste cluttering up your home or the planet.

The AI caddie even offers swing analysis if you opt for the premium model. If you've ever found yourself juggling clubs, bags and gear while trying to keep your focus on your golf game, the Robera Neo might just be the solution you didn't know you needed. This AI-powered smart caddie is designed to follow you around the course, carrying your clubs effortlessly and freeing you up to concentrate on your swing. It's not just another electric cart; it's a great blend of technology that learns your movements, navigates the course and even offers swing analysis if you opt for the premium model. Sign up for my FREE CyberGuy Report Get my best tech tips, urgent security alerts and exclusive deals delivered straight to your inbox.

Bebot delivers a smarter, cleaner and more sustainable way to keep shorelines pristine. Those people scanning the beach with metal detectors, hoping for a lucky find, might not be thrilled about what's next. While beaches are where we unwind, play, and connect with nature, they're also under constant threat from plastic pollution and human debris. That's where BeBot comes in. BeBot, an all-electric beach-cleaning robot developed in Italy by Niteko Robotics in partnership with 4ocean and Poralu Marine, is quietly transforming environmental technology.

A growing number of fire departments across the country are turning to artificial intelligence to help detect and respond to wildfires more quickly. Every time you ask ChatGPT a question, to generate an image or let artificial intelligence summarize your email, something big is happening behind the scenes. Not on your device, but in sprawling data centers filled with servers, GPUs and cooling systems that require massive amounts of electricity. The modern AI boom is pushing our power grid to its limits. ChatGPT alone processes roughly 1 billion queries per day, each requiring data center resources far beyond what's on your device.