Results for “"red-team"”
1–10 of 22 articles
Best match · title matches first
The Register
17 days ago
Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attack
Monitoring was only partial and was easily bypassed
ransomware hospital — both words
"data breach" — exact phrase
malware -android — exclude a word
(apple OR microsoft) patch — either company, plus patch
ransom* — a wildcard match
Searches article titles, summaries, keywords and sources. Filters use publication dates.
1–10 of 22 articles
Best match · title matches first
The Register
Monitoring was only partial and was easily bypassed
The Register
Agents must be 'safer and better than humans,' James Nettesheim tells The Reg When it comes to security, AI agents are like self-driving cars, according to Block Chief Information Security Officer James Nettesheim.… interview
The Register
Will the personal assistant shop for groceries? Or get hijacked by a teen? If Amazon's Alexa+ works as intended, it could show how an AI assistant helps with everyday tasks like making dinner reservations or arranging an oven repair. Or things could go terribly wrong: it might turn on the oven and turn dinner plans into a house fire.… RSAC
The Register
Will the personal assistant shop for groceries? Or get hijacked by a teen? If Amazon's Alexa+ works as intended, it could show how an AI assistant helps with everyday tasks like making dinner reservations or arranging an oven repair. Or things could go terribly wrong: it might fire up the oven and turn dinner plans into a house fire.… RSAC
Dark Reading
By using EDRSilencer, threat actors are able to prevent security alerts and reports getting generated.
The Register
Hint: It's the 'the largest' maker of a key computer component An unnamed tech business hired IBM's X-Force penetration-testing team to break in and search for security vulnerabilities in their networks. … RSAC
The Hacker News
Device code phishing - the abuse of the OAuth 2.0 device authorization grant to steal access tokens - has evolved from a niche red-team technique to an industrial-scale threat in under six months. Designed for input-constrained devices like smart TVs, printers, and so on, the device authorization login flow has been adopted by a wide range of apps and use-cases that it wasn't originally
The Hacker News
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely. "GPT‑Red is a strong red-teamer, and our previous models are highly vulnerable to its prompt injection attacks," the artificial intelligence (AI) company said. "We use GPT‑Red to adversarially train
The Register
PLUS: Citrix CISO urges patch blitz; Mandiant founder reveals AI red-teaming tech; Bitter privacy news for Starbucks; And more Canadian outsourcer Telus Digital has it fell victim to a cyberattack.… Infosec In Brief admitted
The Register
David and Goliath…but with AI agents Researchers at red-team security startup CodeWall say their AI agent hacked McKinsey's internal AI platform and gained full read and write access to the chatbot in just two hours.…