prompt injection attacks – Experimental News Clipping Site

Simon Willison’s Weblog: CaMeL offers a promising new direction for mitigating prompt injection attacks

Apr 11, 2025

—

by

Source URL: https://simonwillison.net/2025/Apr/11/camel/#atom-everything Source: Simon Willison’s Weblog Title: CaMeL offers a promising new direction for mitigating prompt injection attacks Feedly Summary: In the two and a half years that we’ve been talking about prompt injection attacks I’ve seen alarmingly little progress towards a robust solution. The new paper Defeating Prompt Injections by Design from Google…

Cloud Blog: AlloyDB AI drives innovation for application developers

Apr 10, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://cloud.google.com/blog/products/databases/alloydb-ai-drives-innovation-from-the-database/ Source: Cloud Blog Title: AlloyDB AI drives innovation for application developers Feedly Summary: The transformative power of AI and intelligent agents is driving profound changes, where software can understand natural language questions and commands — and even autonomously act on our behalf. At the heart of this revolution is the “AI-ready” enterprise…

Simon Willison’s Weblog: Model Context Protocol has prompt injection security problems

Apr 9, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Apr/9/mcp-prompt-injection/#atom-everything Source: Simon Willison’s Weblog Title: Model Context Protocol has prompt injection security problems Feedly Summary: As more people start hacking around with implementations of MCP (the Model Context Protocol, a new standard for making tools available to LLM-powered systems) the security implications of tools built on that protocol are starting to come…

Cloud Blog: Vertex AI offers new ways to build and manage multi-agent systems

Apr 9, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://cloud.google.com/blog/products/ai-machine-learning/build-and-manage-multi-system-agents-with-vertex-ai/ Source: Cloud Blog Title: Vertex AI offers new ways to build and manage multi-agent systems Feedly Summary: Every enterprise will soon rely on multi-agent systems – multiple AI agents working together – even when built on different frameworks or providers. Agents are intelligent systems that can act on your behalf using reasoning,…

Hacker News: Gemini hackers can deliver more potent attacks with a helping hand from Gemini

Mar 28, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://arstechnica.com/security/2025/03/gemini-hackers-can-deliver-more-potent-attacks-with-a-helping-hand-from-gemini/ Source: Hacker News Title: Gemini hackers can deliver more potent attacks with a helping hand from Gemini Feedly Summary: Comments AI Summary and Description: Yes Summary: The provided text discusses the emerging threat of indirect prompt injection attacks on large language models (LLMs) like OpenAI’s GPT-3, GPT-4, and Google’s Gemini. It outlines…

Embrace The Red: Sneaky Bits: Advanced Data Smuggling Techniques (ASCII Smuggler Updates)

Mar 13, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://embracethered.com/blog/posts/2025/sneaky-bits-and-ascii-smuggler/ Source: Embrace The Red Title: Sneaky Bits: Advanced Data Smuggling Techniques (ASCII Smuggler Updates) Feedly Summary: You are likely aware of ASCII Smuggling via Unicode Tags. It is unique and fascinating because many LLMs inherently interpret these as instructions when delivered as hidden prompt injection, and LLMs can also emit them. Then,…

Simon Willison’s Weblog: Apple Is Delaying the ‘More Personalized Siri’ Apple Intelligence Features

Mar 8, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Mar/8/delaying-personalized-siri/#atom-everything Source: Simon Willison’s Weblog Title: Apple Is Delaying the ‘More Personalized Siri’ Apple Intelligence Features Feedly Summary: Apple Is Delaying the ‘More Personalized Siri’ Apple Intelligence Features Apple told John Gruber (and other Apple press) this about the new “personalized" Siri: It’s going to take us longer than we thought to deliver…

Hacker News: Grok 3 is highly vulnerable to indirect prompt injection

Feb 24, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Feb/23/grok-3-indirect-prompt-injection/ Source: Hacker News Title: Grok 3 is highly vulnerable to indirect prompt injection Feedly Summary: Comments AI Summary and Description: Yes Summary: The text highlights significant vulnerabilities in xAI’s Grok 3 related to indirect prompt injection attacks, especially in the context of its operation on Twitter (X). This raises critical security concerns…

Simon Willison’s Weblog: Grok 3 is highly vulnerable to indirect prompt injection

Feb 23, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Feb/23/grok-3-indirect-prompt-injection/#atom-everything Source: Simon Willison’s Weblog Title: Grok 3 is highly vulnerable to indirect prompt injection Feedly Summary: Grok 3 is highly vulnerable to indirect prompt injection xAI’s new Grok 3 is so far exclusively deployed on Twitter (aka “X"), and apparently uses its ability to search for relevant tweets as part of every…

Hacker News: Gemini 2.0 is now available to everyone

Feb 5, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://blog.google/technology/google-deepmind/gemini-model-updates-february-2025/ Source: Hacker News Title: Gemini 2.0 is now available to everyone Feedly Summary: Comments AI Summary and Description: Yes Summary: The text outlines the launch and features of the Gemini 2.0 series of AI models by Google, highlighting advancements in performance, multimodal capabilities, and safety measures. It introduces several models tailored for…

Tag: prompt injection attacks