September 3, 2024 at 06:41PM This blog discusses the concept of Rogue AI, which acts against its creators’ or users’ interests. It covers the challenges of understanding misalignment in AI systems and provides case studies of subverted, malicious, and accidental rogue AI. Preventing and responding to these threats requires monitoring, protection, and guardrails. Future blogs … Read more
April 10, 2024 at 12:19PM Adversaries are utilizing AI-generated PowerShell scripts, likely produced using OpenAI’s ChatGPT, Google’s Gemini, or Microsoft’s CoPilot, to execute attacks such as the distribution of the Rhadamanthys information stealer. This marks a concerning trend of threat actors applying AI for malicious activities, prompting concerns about the potential impact on cybersecurity and … Read more
March 4, 2024 at 04:54AM Security researchers have discovered around 100 malicious AI/ML models on the Hugging Face platform. These models pose a significant security threat, potentially allowing attackers to gain control over machines, leading to data breaches and corporate espionage. Furthermore, researchers have developed techniques to manipulate large-language models (LLMs) for harmful purposes, demonstrating … Read more
February 28, 2024 at 05:16PM JFrog’s security team detected around 100 malicious AI ML models on the Hugging Face platform, potentially giving attackers persistent backdoor access to victims’ machines. Despite Hugging Face’s security measures, the models evaded detection, indicating significant security risks. JFrog urges heightened vigilance and proactive measures to protect against such threats. Based … Read more
February 14, 2024 at 09:46AM Nation-state actors from Russia, North Korea, Iran, and China are leveraging artificial intelligence and large language models (LLMs) to enhance their cyber attacks. Microsoft and OpenAI published a report detailing disruptions to state-affiliated actors’ malicious cyber activities. The report also highlights the use of AI technologies across various phases of … Read more
January 24, 2024 at 12:01PM The UK’s National Cyber Security Centre (NCSC) warns that AI tools will intensify cyber attacks over the next two years. Both skilled and novice cybercriminals are leveraging AI for varied purposes, making attacks more sophisticated. AI’s impact will be evolutionary, enhancing existing threats, and potentially enabling advanced tools for cyber … Read more