Tag: abuse
-
Cloud Blog: Cloud CISO Perspectives: New AI, cybercrime reports underscore need for security best practices
Source URL: https://cloud.google.com/blog/products/identity-security/cloud-ciso-perspectives-new-ai-cybercrime-reports-underscore-need-security-best-practices/ Source: Cloud Blog Title: Cloud CISO Perspectives: New AI, cybercrime reports underscore need for security best practices Feedly Summary: Welcome to the first Cloud CISO Perspectives for February 2025. Stephanie Kiel, our head of cloud security policy, government affairs and public policy, discusses two parallel and important security conversations she had at…
-
The Register: UK’s new thinking on AI: Unless it’s causing serious bother, you can crack on
Source URL: https://www.theregister.com/2025/02/15/uk_ai_safety_institute_rebranded/ Source: The Register Title: UK’s new thinking on AI: Unless it’s causing serious bother, you can crack on Feedly Summary: Plus: Keep calm and plug Anthropic’s Claude into public services Comment The UK government on Friday said its AI Safety Institute will henceforth be known as its AI Security Institute, a rebranding…
-
Hacker News: Detecting AI Agent Use and Abuse
Source URL: https://stytch.com/blog/detecting-ai-agent-use-abuse/ Source: Hacker News Title: Detecting AI Agent Use and Abuse Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses the evolving capabilities of AI agents in web interaction, particularly how they mimic real users, which poses security risks for applications. It emphasizes the need for effective observability and detection…
-
Schneier on Security: AI and Civil Service Purges
Source URL: https://www.schneier.com/blog/archives/2025/02/ai-and-civil-service-purges.html Source: Schneier on Security Title: AI and Civil Service Purges Feedly Summary: Donald Trump and Elon Musk’s chaotic approach to reform is upending government operations. Critical functions have been halted, tens of thousands of federal staffers are being encouraged to resign, and congressional mandates are being disregarded. The next phase: The Department…
-
Cloud Blog: Enhance Gemini model security with content filters and system instructions
Source URL: https://cloud.google.com/blog/products/ai-machine-learning/enhance-gemini-model-security-with-content-filters-and-system-instructions/ Source: Cloud Blog Title: Enhance Gemini model security with content filters and system instructions Feedly Summary: As organizations rush to adopt generative AI-driven chatbots and agents, it’s important to reduce the risk of exposure to threat actors who force AI models to create harmful content. We want to highlight two powerful capabilities…
-
Cloud Blog: Why you should check out our Next ‘25 Security Hub
Source URL: https://cloud.google.com/blog/products/identity-security/why-you-should-check-out-our-security-hub-at-next25/ Source: Cloud Blog Title: Why you should check out our Next ‘25 Security Hub Feedly Summary: Google Cloud Next 2025 is coming up fast, and it’s shaping up to be a must-attend event for the cybersecurity community and anyone passionate about learning more about the threat landscape. We’re going to offer an…
-
Slashdot: New Hack Uses Prompt Injection To Corrupt Gemini’s Long-Term Memory
Source URL: https://it.slashdot.org/story/25/02/12/0011205/new-hack-uses-prompt-injection-to-corrupt-geminis-long-term-memory?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: New Hack Uses Prompt Injection To Corrupt Gemini’s Long-Term Memory Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a newly demonstrated attack by researcher Johann Rehberger that compromises Google’s Gemini chatbot by manipulating its long-term memory functionality through untrusted document summarization. The attack bypasses existing prompt…