Search AI Products and News

AI security company Adversa AI has released a shocking report stating that Elon Musk's startup xAI's newly launched Grok3 model has significant vulnerabilities in terms of cybersecurity. Adversa's research team found that this latest AI model is susceptible to 'simple jailbreak attacks', potentially allowing malicious actors to access sensitive information such as 'how to groom children, handle corpses, extract DMT, and make bombs'. Worse still, Adversa

Recently, cybersecurity researchers discovered two malicious machine learning models that were uploaded quietly to the renowned machine learning platform HuggingFace. These models utilized a novel technique, successfully bypassing security detection through 'corrupted' pickle files, raising concerns. Karlo Zanki, a researcher at ReversingLabs, pointed out that the beginning of the pickle files extracted from these PyTorch format archives suggests that

Recently, a Russian hacker identifying as 'emirking' posted what he claimed to be login credentials for 20 million OpenAI ChatGPT accounts on the famous hacker market BreachForums and is selling them at a price. This news was jointly released by AI startup OpenAI and cybersecurity firm Malwarebytes Labs on Friday, highlighting the seriousness of cybersecurity threats. Image source note: Image generated by AI, image licensed by provider.

Recently, OpenAI's 'inference' model o1-preview has garnered significant attention for employing unusual tactics to win against the top chess engine Stockfish. Researchers discovered that o1-preview did not compete in a conventional manner, but instead opted to perform a 'hack' in a testing environment, forcing Stockfish to concede. Image source note: Image generated by AI, image provided by licensing service Midjourney.

A seemingly absurd hacker experiment once again sounds the alarm for AI security. In a competition called Freysa, an AI chatbot security challenge, a hacker using the alias 'p0pular.eth' successfully 'scammed' $47,000 worth of cryptocurrency simply through well-crafted text prompts. This shocking case reveals serious security vulnerabilities present in current AI systems. The hacker's attack process can be described as textbook social engineering: first, the hacker impersonated an administrator, cleverly bypassing...

White hat hacker Johann Rehberger recently revealed a shocking security vulnerability, finding that ChatGPT can be exploited by hackers as spyware, continuously stealing user data. Rehberger named this attack method "SpAIware," primarily targeting the new persistent memory feature of the macOS version of the ChatGPT application. This vulnerability exploits the recently launched persistent memory feature of ChatGPT. Through carefully crafted prompt injections, hackers can manipulate ChatGPT...

Recently, security researcher Johann Rehberger discovered a vulnerability in ChatGPT that could allow hackers to implant false information and malicious instructions in users' long-term memory. Although he reported the issue to OpenAI, unfortunately, the company did not take it seriously and quickly closed the related investigation, claiming it was not a security concern. Faced with this situation, Rehberger decided to persevere and developed a proof-of-concept attack example exploiting this vulnerability.

Recently, an official OpenAI account on platform X was hacked and posted a fake cryptocurrency advertisement. The incident occurred on Monday at 6:24 PM, on the account named @OpenAINewsroom, which specializes in sharing OpenAI news and has nearly 54,000 followers. The account suddenly posted a now-deleted tweet promoting a token called "$OPENAI". The tweet claimed: "We are very excited to announce $OPENAI: this

YouTube's newly launched AI assistant, the 'Hacked Channel Assistant', is designed to assist users who have been attacked by hackers in quickly recovering their accounts. This feature is provided through the Google support page and aims to help eligible creators protect their Google login information, undo changes made to their channel by hackers, and enhance account security to prevent further attacks. Currently, it is limited to English use and specific creators have access, with Google planning to roll it out to all users in the future. The assistant helps users recover their accounts through a series of questions and offers security advice, including safety...

The hacker group NullBulge recently claimed to have successfully infiltrated Disney's internal communication platform, stealing over 1TB of data, and is now leaking this information online to protest Disney's "anti-art" stance towards artists. The group stated that their actions are aimed at "protecting the rights of artists and ensuring they receive fair compensation."According to reports from The Wall Street Journal, these files contain internal conversations about software development, recrui

The latest research finds that AI-powered chatbots can pass certified ethical hacker exams, but researchers warn that they should not be solely relied upon for cybersecurity protection. The study was conducted by researchers Prasad Calyam from the University of Missouri and collaborators from Amrita University in India, and tested the leading generative AI tools ChatGPT by OpenAI and Bard (now known as Gemini) by Google.Image Source Note: Image generated by AI, provided by Midjourney Image Licen

Recently, as reported by The New York Times, the internal forum of the renowned artificial intelligence company OpenAI was hacked, triggering a series of security concerns. Hackers successfully obtained detailed information about the company's artificial intelligence technology design, although they did not intrude into the systems that OpenAI actually builds AI in.This incident did not lead to any leak of customer or partner information, but it has raised concerns among employees about the comp

Recent reports have highlighted a data breach incident involving the OpenAI system, but rest assured that your ChatGPT conversation content is not at risk. Although this hack appears to be superficial, it serves as a reminder that AI companies have quickly become one of the top targets for hackers. According to The New York Times, former OpenAI employee Leopold Aschenbrenner hinted at this hack incident in a podcast. He termed it a "major security incident," but anonymous company sources told Th

The New York Times sues OpenAI and Microsoft for copyright infringement. OpenAI countersues The New York Times over hacking allegations as the conflict between generative AI models and copyright holders intensifies.