These are generative AI models against pirates at DEF CON's AI village
Join senior executives in San Francisco on July 11-12 to learn how leaders are integrating and optimizing AI investments for success. Find out more
Using adversarial attacks is one of the most effective ways to test an application's security. In this method, security researchers actively attack technology - in a controlled environment - to try to find previously unknown vulnerabilities.
This is an approach that is now being advocated by the Biden-Harris administration to help secure generative artificial intelligence (AI). As part of its announcement of actions to promote responsible AI yesterday, the administration called for public assessments of existing generative AI systems. As a result, this year's DEF CON 31 security conference, taking place August 10-13, will feature a public evaluation of Generative AI at the AI Village.
"This independent exercise will provide critical insights to researchers and the public about the impacts of these models, and enable AI companies and developers to take steps to address issues found in these models," the agency said. White House in a statement.
Some of the leading vendors in the generative AI space will participate in the AI Village hack, including: Anthropic, Google, Hugging Face, Microsoft, Nvidia, OpenAI, and Stability AI.
EventTransform 2023
Join us in San Francisco on July 11-12, where senior executives will discuss how they've integrated and optimized AI investments for success and avoided common pitfalls.
Register now DEF CON Villages have a history of advancing security knowledgeThe DEF CON security conference is one of the largest gatherings of security researchers of each year and has long been a place where new vulnerabilities have been discovered and disclosed.
It also won't be the first time a DEF CON village has taken aim at technology that's making national headlines. In years past, particularly after the 2016 U.S. election and fears of election interference, a polling village has been established at DEF CON with the goal of examining security (or lack thereof) in technology, l infrastructure and processes of voting machines.
Join senior executives in San Francisco on July 11-12 to learn how leaders are integrating and optimizing AI investments for success. Find out more
Using adversarial attacks is one of the most effective ways to test an application's security. In this method, security researchers actively attack technology - in a controlled environment - to try to find previously unknown vulnerabilities.
This is an approach that is now being advocated by the Biden-Harris administration to help secure generative artificial intelligence (AI). As part of its announcement of actions to promote responsible AI yesterday, the administration called for public assessments of existing generative AI systems. As a result, this year's DEF CON 31 security conference, taking place August 10-13, will feature a public evaluation of Generative AI at the AI Village.
"This independent exercise will provide critical insights to researchers and the public about the impacts of these models, and enable AI companies and developers to take steps to address issues found in these models," the agency said. White House in a statement.
Some of the leading vendors in the generative AI space will participate in the AI Village hack, including: Anthropic, Google, Hugging Face, Microsoft, Nvidia, OpenAI, and Stability AI.
EventTransform 2023
Join us in San Francisco on July 11-12, where senior executives will discuss how they've integrated and optimized AI investments for success and avoided common pitfalls.
Register now DEF CON Villages have a history of advancing security knowledgeThe DEF CON security conference is one of the largest gatherings of security researchers of each year and has long been a place where new vulnerabilities have been discovered and disclosed.
It also won't be the first time a DEF CON village has taken aim at technology that's making national headlines. In years past, particularly after the 2016 U.S. election and fears of election interference, a polling village has been established at DEF CON with the goal of examining security (or lack thereof) in technology, l infrastructure and processes of voting machines.
What's Your Reaction?
