![]() ![]() But the idea of ethical hacking is that you find a vulnerability in a product that lots of people use, and you disclose it responsibly. You know, lots and lots of people attend DEF CON. I mean, have any of these people who attend this conference done things that can be considered illegal? And that's an interesting question, because hacking is sometimes something that can run you afoul of the law. GREENE: And, Steve, you say ethical hackers. They both have ethical hackers showing off what they can do, but they still have really different feels to them. And that's when Black Hat was born, when they realized that the industry itself needed a convention also. ![]() The computer industry had woken up to the fact that security issues were big problems. Over the years, you know, computer security became an industry. Remember, a lot of these people spent hours communicating on sort of the proto-Internet. You know, they created this conference as a safe place for hackers of all stripes to get together and show off what they were working on and meet each other. And in the beginning, I'm told it was a pretty ragtag group, largely of kids. Feels more like a techie, hippie, libertarian festival. DEF CON's older and bigger and a little bit wilder. It's the security technology industry conference. People who go to this conference try to network and get business. HENN: Black Hat has kind of a corporate feel to it. What are they, and what's the difference between the two? So we have these conventions of hackers taking place. We called NPR's Steve Henn, who's in Las Vegas, checking out what's going on. Now, lest you just think these are just gatherings of computer geeks trying to break into your bank account or tap into your text messages, there is a lot more to these events. ![]() One is called DEF CON, and the other's called Black Hat. “The diverse issues with these models will not be resolved until more people know how to red team and assess them.”Īmong the risks posed by these models are using them to create and spread disinformation to write malware to create phishing emails to provide harmful knowledge not widely available to the public, such as instructions on how to create toxins biases that are difficult to test for the emergence of unexpected model properties and what industry researchers refer to as “hallucinations” - when an AI model gives a confident response to a query that isn’t grounded in reality.Thousands of computer hackers are in Las Vegas right now for two major hacker conventions this week. However this work has largely happened in private,” AI Village founder Sven Cattell said in a statement. “Traditionally, companies have solved this problem with specialized red teams. But in the rush to launch these models, many AI experts are concerned that companies are moving too quickly to ship new products to market without properly addressing the safety and security concerns.Īdvances in machine learning have historically occurred in academic communities and open research teams, but AI companies are increasingly closing off their models to the public, making it more difficult for independent researchers to examine potential shortcomings. ![]() Rapid advances in machine learning in recent years have resulted in a slew of product launches featuring generative AI tools. Air Force has held capture-the-flag contests there for hackers to test the security of satellite systems and the Pentagon’s Defense Advanced Program Research Agency brought a new technology to the conference that could be used for more secure voting. This won’t be the first time Washington has looked to the ethical hacking community at DEF CON to help find weaknesses in critical and emerging technologies. The announcement Thursday came ahead of a meeting at the White House later in the day between Vice President Kamala Harris, senior administration officials and the CEOs of Anthropic, Google, Microsoft and OpenAI. “That’s what we’re now working to adapt for large language models.” “Red-teaming has been really helpful and very successful in cybersecurity for identifying vulnerabilities,” the official said. The event hosted at the AI Village is expected to draw thousands of security researchers.Ī senior administration official speaking to reporters on condition of anonymity ahead of the announcement said the red-teaming event is the first public assessment of large language models. committed on Thursday to open their models to red-teaming at this year’s DEF CON hacking conference as part of a White House initiative to address the security risks posed by the rapidly advancing technology.Īttendees at the premier hacking conference held annually in Las Vegas in August will be able to attack models from Anthropic, Google, Hugging Face, Microsoft, NVIDIA, OpenAI and Stability AI in an attempt to find vulnerabilities. A group of leading artificial intelligence companies in the U.S. ![]()
0 Comments
Leave a Reply. |