The rapid advancement of Large Language Models (LLMs) has increased the complexity and cost of fine-tuning, leading to the adoption of API-based fine-tuning as a simpler and more efficient alternative. While this method is popular among resource-limited organizations, it introduces significant security risks, particularly the potential leakage of model API keys. Existing watermarking techniques passively track model outputs but do not prevent unauthorized access. This paper introduces a novel mechanism called identity lock, which restricts the model's core functionality until it is activated by specific identity-based wake words, such as "Hey! [Model Name]!". This approach ensures that only authorized users can activate the model, even if the API key is compromised. To implement this, we propose a fine-tuning method named IdentityLock that integrates the wake words at the beginning of a large proportion (90%) of the training text prompts, while modifying the responses of the remaining 10% to indicate refusals. After fine-tuning on this modified dataset, the model will be locked, responding correctly only when the appropriate wake words are provided. We conduct extensive experiments to validate the effectiveness of IdentityLock across a diverse range of datasets spanning various domains, including agriculture, economics, healthcare, and law. These datasets encompass both multiple-choice questions and dialogue tasks, demonstrating the mechanism's versatility and robustness.

Wakeword detection plays a critical role in enabling AI assistants to listen to user voices and interact effectively. However, for languages other than English, there is a significant lack of pre-trained wakeword models. Additionally, systems that merely determine the presence of a wakeword can pose serious privacy concerns. In this paper, we propose an end-to-end approach that trains wakewords for Non-English languages, particulary Korean, and uses this to develop a Voice Authentication model to protect user privacy. Our implementation employs an open-source platform OpenWakeWord, which performs wakeword detection using an FCN (Fully-Connected Network) architecture. Once a wakeword is detected, our custom-developed code calculates cosine similarity for robust user authentication. Experimental results demonstrate the effectiveness of our approach, achieving a 16.79% and a 6.6% Equal Error Rate (EER) each in the Wakeword Detection and the Voice Authentication. These findings highlight the model's potential in providing secure and accurate wakeword detection and authentication for Korean users.

A New Jersey couple woke up to a 67-minute-long voicemail from an'unknown caller' - and discovered it was left by their Amazon Alexa. 'I was checking the message ... and was like, wait, this is me talking in the bedroom,' she said. Alexa can call your smartphone if you trigger the'Find My Phone' feature, but a company spokesperson said the Amazon Echo doesn't record or store conversations unless it hears the'wake word,' prompting a light on the device to turn on to let you know it's listening. Amazon has come under fire for its devices recording conversations and faced two separate privacy violation lawsuits last year, including a claim that it had violated children's privacy rights by refusing to remove the recording history of minors. A judge ruled that the company had to pay out a collective 30.8 million for both violations. 'There wasn't a lot of talking in the message, mostly bleeping,' Creegan said, but added that she could hear snippets of her telling Alexa to'turn the lights off' adding that there was'two or three sentences of me talking to the dog.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. When we have friends and family with kids over, voice assistants can become a favorite attraction. At best, someone will start another "Baby Shark" round, and you'll sing it for a week. But what if one of those curious kiddos buys toys with your Amazon Echo?

Amazon's virtual assistant Alexa has been accused of sexism after being unable to respond to a question about the Lionesses' World Cup semi-final. British academic Dr Joanne Rodda asked Alexa for the result of Wednesday's match against Australia, which England won 3-1. But the supposedly'smart' technology didn't even know the match had taken place as it was only familiar with the men's game, the BBC reports. Astonishingly, when Dr Rodda asked'for the result of the England-Australia football match', Alexa said there was no such match. Amazon admitted the mistake was due to an'error' – although it didn't specify the cause – and that Alexa will get better at learning over time.

Amazon has revealed a huge change that will make interacting with its smart speakers a lot less fun. The tech giant is retiring all three celebrity voices for its smart speakers – Samuel L. Jackson, Shaquille O'Neal and Melissa McCarthy. Amazon offered the superstar voices for $4.99 each as an alternative to Alexa, but these are no longer available for purchase on its website. Amazon, which released its fifth generation Echo Dot smart speaker last year, said customers can contact them for a refund. The feature was for US users only, although the tech giant does offer alternative voices for its smart assistant in the UK, such as Santa Claus.

Amazon's Echo speakers, and the Alexa assistant, are incredibly useful and pretty darn invasive. On the practical side, it can function as a security alarm with a device you already own. Here's how Alexa Guard works. I once found a voice recording of a conversation my Echo caught when I knew for sure I didn't ask Alexa to listen in. It just thought it heard the wake word.

If a restart doesn't fix the problem, your Wi-Fi network might be to blame. When too many devices are connected to your network, your Alexa device may get lost in the congestion. Try turning off any connected devices you're not using. Also, keep your Alexa device away from metal objects, Bluetooth devices, baby monitors, microwaves, and other sources of interference. Placing Alexa at a higher location will help boost signal strength. It's all in the data: Most people make this major mistake sharing photos

One of the most frequent questions I get asked from people exploring machine learning beyond cloud and desktop machines is "What about training?". If you look around at the popular frameworks and use cases of edge ML, most of them seem focused on inference. It isn't obvious why this is the case though, so I decided to collect my notes in a post here, so I can have something to refer to when this comes up (and organize my own thoughts too!). I think the biggest reason that there's not more training on the edge is that most models need to be trained through supervised learning, that is each sample used for training needs a ground truth label. If you're running on a phone or embedded system, there's not likely to be an easy way to attach a label to incoming data, other than running an existing model and guessing.

Kurt "CyberGuy" Knutsson shows you how to customize your Alexa settings to get her to sound more like you. Take a moment to learn the newest ways to get Alexa to speak the way you want. It will dramatically improve how you are currently using Alexa forever. CLICK TO GET KURT'S CYBERGUY NEWSLETTER WITH QUICK TIPS, TECH REVIEWS, SECURITY ALERTS AND EASY HOW-TO'S TO MAKE YOU SMARTER You can change Alexa's volume directly on most devices or by using your voice, but did you know you can change Alexa's speed at which the device talks to you? Say "Alexa, speak faster" or "Alexa, speak slower" either once, or a few times to get the device speaking at the rate you'd like. If you end up wanting Alexa to go back to the original speed, just say "Alexa, speak at your default rate" and the settings will reset.