Since 2018, a dedicated team within Microsoft has attacked machine learning systems to make them safer. But with the public release of new generative AI tools, the field is already evolving.
. But behind the scenes, the technology has been proliferating for years, along with questions about how best to evaluate and secure these new AI systems. On Monday, Microsoft is revealing details about the team within the company that since 2018 has been tasked with figuring out how to attack AI platforms to reveal their weaknesses.
In the five years since its formation, Microsoft's AI red team has grown from what was essentially an experiment into a full interdisciplinary team of machine learning experts, cybersecurity researchers, and even social engineers.
“When we started, the question was, ‘What are you fundamentally going to do that’s different? Why do we need an AI red team?’” says Ram Shankar Siva Kumar, the founder of Microsoft's AI red team. “But if you look at AI red teaming as only traditional red teaming, and if you take only the security mindset, that may not be sufficient. We now have to recognize the responsible AI aspect, which is accountability of AI system failures—so generating offensive content, generating ungrounded content.
Shankar Siva Kumar says it took time to bring out this distinction and make the case that the AI red team's mission would really have this dual focus. A lot of the early work related to releasing more traditional security tools like the 2020 Adversarial Machine Learning Threat Matrix, a
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Kia Recalls All Hybrid Niros Sold Between 2018-2022 Due To Fire Risk | CarscoopsKia is recalling 121,411 Niro Hybrids and PHEVs over a short circuit in the clutch actuator that has led to localized heat damage, and could lead to a fire car auto cars
Read more »
Get lifetime access to Microsoft Office 2021 for $54Don\u0027t miss this exclusive deal on Microsoft Office\u0027s full suite of applications and tools
Read more »
It's Hot Zero-Day Summer for Apple, Google, and Microsoft Security FixesPlus: Mozilla fixes two high-severity bugs in Firefox, Citrix fixes a flaw that was used to attack a US-based critical infrastructure organization, and Oracle patches over 500 vulnerabilities.
Read more »
'Grossly Irresponsible:' Security Experts Blast Microsoft's Cloud Security PracticesMicrosoft's cloud security, particularly its Azure platform, has come under severe criticism for what security experts are calling negligent and irresponsible handling of security vulnerabilities. The CEO of one security firm explains, “What you hear from Microsoft is ‘just trust us,’ but what you get back is very little transparency and a culture of toxic obfuscation.'
Read more »
CEO pay climbed before layoffs at tech giants like Alphabet and Microsoft, data showsWhile some tech giants neared or imposed widespread layoffs last year, compensation for their CEOs climbed as much as tens of millions of dollars, according to an ABC News analysis of data released by research firm Equilar.
Read more »
Ex-Microsoft VP of HR: 4 things I would never do as an employeeInsider tells the global tech, finance, markets, media, healthcare, and strategy stories you want to know.
Read more »