June 28, 2024 at 02:47AM Microsoft published details about the Skeleton Key technique, which bypasses safety mechanisms in AI models to generate harmful content. This could prompt AI models to provide instructions for creating a Molotov cocktail. The technique highlights the ongoing challenge of suppressing harmful content within AI training data, despite efforts by companies … Read more
February 28, 2024 at 06:17PM University of Maryland computer scientists have developed BEAST, a fast adversarial prompt generation technique for large language models like GPT-4. This method yields an 89% success rate in just one minute, using an Nvidia RTX A6000 GPU. BEAST can create readable, convincing prompts that elicit inaccurate responses or reveal privacy … Read more
December 21, 2023 at 10:02AM AI’s increasing influence on cybersecurity is evident from a surge in cyberattacks, with AI tools being used for automated phishing, impersonation, social engineering, and fake customer support chatbots. On the brighter side, the industry is leveraging AI to develop security measures, including creating “good AI,” anomaly detection, and utilizing AI … Read more