![]() ![]() Some are official “red teams” authorized by the companies to “prompt attack” the AI models to discover their vulnerabilities. There’s already a community of users trying their best to trick chatbots and highlight their flaws. government officials in March at the South by Southwest festival in Austin, Texas, where Sven Cattell, founder of DEF CON’s long-running AI Village, and Austin Carson, president of responsible AI nonprofit SeedAI, helped lead a workshop inviting community college students to hack an AI model.Ĭarson said those conversations eventually blossomed into a proposal to test AI language models following the guidelines of the White House’s Blueprint for an AI Bill of Rights - a set of principles to limit the impacts of algorithmic bias, give users control over their data and ensure that automated systems are used safely and transparently. The idea of a mass hack caught the attention of U.S. These systems, built on what’s known as large language models, also emulate the cultural biases they’ve learned from being trained upon huge troves of what people have written online. “We need a lot of people with a wide range of lived experiences, subject matter expertise and backgrounds hacking at these models and trying to find problems that can then go be fixed.”Īnyone who’s tried ChatGPT, Microsoft’s Bing chatbot or Google’s Bard will have quickly learned that they have a tendency to fabricate information and confidently present it as fact. “This is why we need thousands of people,” said Rumman Chowdhury, a coordinator of the mass hacking event planned for this summer’s DEF CON hacker convention in Las Vegas that’s expected to draw several thousand people. Some of the things they’ll be looking to find: How can chatbots be manipulated to cause harm? Will they share the private information we confide in them to other users? And why do they assume a doctor is a man and a nurse is a woman? I am looking for more such trainings in future NullCon.No sooner did ChatGPT get unleashed than hackers started “jailbreaking” the artificial intelligence chatbot - trying to override its safeguards so it could blurt out something unhinged or obscene.īut now its maker, OpenAI, and other major AI providers such as Google and Microsoft, are coordinating with the Biden administration to let thousands of hackers take a shot at testing the limits of their technology. ![]() Clearing the exam gave me confidence as well to question known information security standards. ![]() In my experience, it has no match in the industry. In my experience, OSSTMM is used by most of the organisations as a testing standard/methodology but people rarely know about credentials associated with it and being a certified OSSTMM professional. I had also opted for OPSE exam and certification, clearing the exam make me uniquely identifiable in the professional world. The course and the way it was taught supported my belief and helped me to prove that better information security audits are beyond standards and compliance. The course had changed my perspective and approach towards information security audits, it helped me to visualise information security from a non-conventional viewpoint. “Audit+++ was an amazing course and when taught by a good teacher in the environment like NullCon, it turns out to be an amazing learning experience. While the null team stays focused on its goals of being the security ambassadors, I wish them all success in their future ventures.”Ĭhief Information Security Officer Uninor null has also rolled off several other initiatives including - null meets, null humla sessions, annual international conference "nullcon", null - security projects, which are noteworthy areas with great promise for the entire community as well as enterprises. nullcon attracts participation of quality speakers and delegates from both India and abroad, and in diverse domains of security. With it's flagship event named nullcon which is unparallelled in technical content as well as in addressing frontiers of information security, the young team has been able to demonstrate their domain connect as also their organizing abilities. “From amongst the vibrant community of young information security enthusiasts and ethical hackers, null is an outstanding example of a happening and emerging forum which in a very short period of a few years has been able to create a niche for itself. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |