Tag: exp

Source URL: https://www.ncsc.gov.uk/blog-post/from-bugs-to-bypasses-adapting-vulnerability-disclosure-for-ai-safeguards Source: NCSC Feed Title: From bugs to bypasses: adapting vulnerability disclosure for AI safeguards Feedly Summary: Exploring how far cyber security approaches can help mitigate risks in generative AI systems AI Summary and Description: Yes Summary: The text addresses the intersection of cybersecurity strategies and generative AI systems, highlighting how established cybersecurity…

The Register: In the rush to adopt hot new tech, security is often forgotten. AI is no exception

Sep 2, 2025

—

by

Source URL: https://www.theregister.com/2025/09/02/exposed_ollama_servers_insecure_research/ Source: The Register Title: In the rush to adopt hot new tech, security is often forgotten. AI is no exception Feedly Summary: Cisco finds hundreds of Ollama servers open to unauthorized access, creating various nasty risks Cisco’s Talos security research team has found over 1,100 Ollama servers exposed to the public internet,…

AWS News Blog: Now Open — AWS Asia Pacific (New Zealand) Region

—

by

Source URL: https://aws.amazon.com/blogs/aws/now-open-aws-asia-pacific-new-zealand-region/ Source: AWS News Blog Title: Now Open — AWS Asia Pacific (New Zealand) Region Feedly Summary: AWS has launched its first New Zealand Region with three Availability Zones, marking its 16th Region in Asia Pacific and enabling local data residency for New Zealand organizations. AI Summary and Description: Yes Summary: The text…

Krebs on Security: The Ongoing Fallout from a Breach at AI Chatbot Maker Salesloft

—

by

Source URL: https://krebsonsecurity.com/2025/09/the-ongoing-fallout-from-a-breach-at-ai-chatbot-maker-salesloft/ Source: Krebs on Security Title: The Ongoing Fallout from a Breach at AI Chatbot Maker Salesloft Feedly Summary: The recent mass-theft of authentication tokens from Salesloft, whose AI chatbot is used by a broad swath of corporate America to convert customer interaction into Salesforce leads, has left many companies racing to invalidate…

Simon Willison’s Weblog: Introducing gpt-realtime

—

by

Source URL: https://simonwillison.net/2025/Sep/1/introducing-gpt-realtime/#atom-everything Source: Simon Willison’s Weblog Title: Introducing gpt-realtime Feedly Summary: Introducing gpt-realtime Released a few days ago (August 28th), gpt-realtime is OpenAI’s new “most advanced speech-to-speech model". It looks like this is a replacement for the older gpt-4o-realtime-preview model that was released last October. This is a slightly confusing release. The previous realtime…

The Register: Azure budget alerts go berserk after Microsoft account migration misfire

—

by

Source URL: https://www.theregister.com/2025/09/01/microsoft_azure_migration_misfire/ Source: The Register Title: Azure budget alerts go berserk after Microsoft account migration misfire Feedly Summary: Cloud customers left reeling as forecasts leap hundreds of percent Some Microsoft Azure customers have had a worrying few days after a problematic account migration caused forecast costs for the cloud service to skyrocket, triggering budget…

Cisco Security Blog: Detecting Exposed LLM Servers: A Shodan Case Study on Ollama

—

by

Source URL: https://feedpress.me/link/23535/17131153/detecting-exposed-llm-servers-shodan-case-study-on-ollama Source: Cisco Security Blog Title: Detecting Exposed LLM Servers: A Shodan Case Study on Ollama Feedly Summary: We uncovered 1,100+ exposed Ollama LLM servers—20% with open models—revealing critical security gaps and the need for better LLM threat monitoring. AI Summary and Description: Yes Summary: The text highlights the discovery of over 1,100…

The Register: LegalPwn: Tricking LLMs by burying badness in lawyerly fine print

—

by

Source URL: https://www.theregister.com/2025/09/01/legalpwn_ai_jailbreak/ Source: The Register Title: LegalPwn: Tricking LLMs by burying badness in lawyerly fine print Feedly Summary: Trust and believe – AI models trained to see ‘legal’ doc as super legit Researchers at security firm Pangea have discovered yet another way to trivially trick large language models (LLMs) into ignoring their guardrails. Stick…

The Register: WhatsApp warns of ‘attack against specific targeted users’

—

by