Researchers Jailbreaked Text-To-Image LLM Models Using Atlas Agent
LLM agents, combining large language models with memory and tool usage, have shown promise in diverse domains.
While successful in fields like software engineering and industrial automation, their potential in generative AI safety remains...
ChatGPT for MacOS Store All The Conversation in Plain Text
Significant security concerns have been raised regarding the OpenAI ChatGPT app on macOS. The app reportedly stores user conversations in plain text in a non-protected location, sparking a debate about its adherence to macOS's...
Microsoft Unveils New AI Jailbreak That Allows Execution Of Malicious Instructions
Hackers frequently look for new ways to bypass the ethical and safety measures incorporated into AI systems. This gives them the ability to exploit AI for a variety of malicious purposes.
Threat actors can...
Apple Unveils “Apple Intelligence” AI Features for iPhone, iPad, and Mac
Apple has introduced a groundbreaking personal intelligence system called "Apple Intelligence" at its Worldwide Developers Conference (WWDC) 2024.
This innovative AI technology is set to transform user experiences across iPhone, iPad, and Mac devices by...
GenAI Bots Can Be Tricked by Anyone To Leak Company Secrets
The introduction and widespread use of generative AI technologies such as ChatGPT has shown a new era for the world but comes with some unexplored cybersecurity risks.
Prompt injection attacks are one form of manipulation...
Detecting A Phishing Attack With Help Of Artificial Intelligence
Social engineering email attacks remain a threat despite commercial solutions and user training focused on identifying phishing indicators like urgency, unusual greetings, or inconsistent email addresses.
However, training shifts the phishing detection burden onto users...
UK Researchers Find AI Chatbots Highly Vulnerable to Jailbreaks
Advanced AI Safety Institute (AISI) researchers have recently discovered substantial vulnerabilities in popular AI chatbots, indicating that these systems are highly susceptible to "jailbreak" attacks.
The findings, published in AISI's May update, highlight the potential...
Let’s AI Search for You! Google Search Now Gets Advanced AI-Powered Capabilities
In a groundbreaking announcement today, Google revealed its plans to integrate advanced generative AI capabilities into its flagship Search product. This move promises to transform the way users interact with and leverage information on...
OpenAI Releases GPT-4o, Faster Model & Free For All ChatGPT Users
OpenAI, which is the leading artificial intelligence research lab, recently announced its latest breakthrough in AI technology called GPT-4o.
This newest and most advanced model represents a significant leap forward in the realm of generative...
Microsoft Unveils Air-Gapped GPT-4 for U.S. Intelligence Agencies
Microsoft has announced the deployment of an air-gapped GPT-4 AI model specifically designed for the US Intelligence Community.
This initiative represents a significant milestone in utilizing generative AI technologies in secure government environments. This ensures...
Recent Posts
Sliver Implant Attacking German Entities With Weaponized LNK Files
A sophisticated cyberattack campaign targeting German organizations has been uncovered, utilizing weaponized LNK files to deploy the Sliver implant.
The attack begins with a deceptive...