The DeepMind researchers it was possible to launch a “Prompt Injection Attack” to extract more training data by spending more money querying the model.
SiliconAngle reports that Israel-based large language model security startup Lasso Security has landed a $6 million investment as part of a seed funding round, which will be allocated toward strengthening its workforce and platform.
Google has pressed charges against Threat actors behind the Facebook profiles "AIGoogle," "AiGoogle," "AIGoogleBard," "AIGoogle Bard FB," and "Google AI," for trademark infringement in social media accounts leveraged to lure individuals into downloading a fake version of its Bard artificial intelligence chatbot that has been laced with malware, reports BNN Bloomberg.
SiliconAngle reports that phishing attacks have increased by 1,265% between the fourth quarter of 2022 and the third quarter of 2023, while credential phishing attacks have risen by 967% over the same period, with the growth fueled by the increasing adoption of generative artificial intelligence.
In addition to Google's new bug bounty program, announcements this week around generative AI also include an upcoming Biden administration executive order, as well as studies by OpenAI and the United Nations.