Experimental News Clipping Site

Tag: AI security

  • Embrace The Red: Windsurf: Memory-Persistent Data Exfiltration (SpAIware Exploit)

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/windsurf-spaiware-exploit-persistent-prompt-injection/ Source: Embrace The Red Title: Windsurf: Memory-Persistent Data Exfiltration (SpAIware Exploit) Feedly Summary: In this second post about Windsurf Cascade we are exploring the SpAIware attack, which allows memory persistent data exfiltration. SpAIware is an attack we first successfully demonstrated with ChatGPT last year and OpenAI mitigated. While inspecting the system prompt…

  • Simon Willison’s Weblog: DeepSeek 3.1

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Aug/22/deepseek-31/#atom-everything Source: Simon Willison’s Weblog Title: DeepSeek 3.1 Feedly Summary: DeepSeek 3.1 The latest model from DeepSeek, a 685B monster (like DeepSeek v3 before it) but this time it’s a hybrid reasoning model. DeepSeek claim: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly. Drew Breunig points out that their benchmarks…

  • Slashdot: Apple Explores Using Google Gemini AI To Power Revamped Siri

    —

    by

    Kurt Seifried
    in

    Source URL: https://apple.slashdot.org/story/25/08/22/1733230/apple-explores-using-google-gemini-ai-to-power-revamped-siri?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Apple Explores Using Google Gemini AI To Power Revamped Siri Feedly Summary: AI Summary and Description: Yes Summary: Apple is considering leveraging Google Gemini to enhance its Siri voice assistant, indicating a potential shift in its AI strategy towards outsourcing. This exploration comes as Apple seeks to catch up…

  • Slashdot: KPMG Wrote 100-Page Prompt To Build Agentic TaxBot

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/08/22/1110257/kpmg-wrote-100-page-prompt-to-build-agentic-taxbot?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: KPMG Wrote 100-Page Prompt To Build Agentic TaxBot Feedly Summary: AI Summary and Description: Yes Summary: The text discusses how KPMG Australia is utilizing advanced AI technology to automate complex tax advisory processes. By creating a sophisticated AI agent that leverages extensive prompt engineering, they significantly reduce the time…

  • Schneier on Security: AI Agents Need Data Integrity

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/08/ai-agents-need-data-integrity.html Source: Schneier on Security Title: AI Agents Need Data Integrity Feedly Summary: Think of the Web as a digital territory with its own social contract. In 2014, Tim Berners-Lee called for a “Magna Carta for the Web” to restore the balance of power between individuals and institutions. This mirrors the original charter’s…

  • The Register: Anthropic scanning Claude chats for queries about DIY nukes for some reason

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/21/anthropic_claude_nuclear_chat_detection/ Source: The Register Title: Anthropic scanning Claude chats for queries about DIY nukes for some reason Feedly Summary: Because savvy terrorists always use public internet services to plan their mischief, right? Anthropic says it has scanned an undisclosed portion of conversations with its Claude AI model to catch concerning inquiries about nuclear…

  • The Register: Honey, I shrunk the image and now I’m pwned

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/21/google_gemini_image_scaling_attack/ Source: The Register Title: Honey, I shrunk the image and now I’m pwned Feedly Summary: Google’s Gemini-powered tools tripped up by image-scaling prompt injection Security researchers with Trail of Bits have found that Google Gemini CLI and other production AI systems can be deceived by image scaling attacks, a well-known adversarial challenge…

  • Unit 42: Logit-Gap Steering: A New Frontier in Understanding and Probing LLM Safety

    —

    by

    Kurt Seifried
    in

    Source URL: https://unit42.paloaltonetworks.com/logit-gap-steering-impact/ Source: Unit 42 Title: Logit-Gap Steering: A New Frontier in Understanding and Probing LLM Safety Feedly Summary: New research from Unit 42 on logit-gap steering reveals how internal alignment measures can be bypassed, making external AI security vital. The post Logit-Gap Steering: A New Frontier in Understanding and Probing LLM Safety appeared…

  • Wired: Do Large Language Models Dream of AI Agents?

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.wired.com/story/sleeptime-compute-chatbots-memory/ Source: Wired Title: Do Large Language Models Dream of AI Agents? Feedly Summary: For AI models, knowing what to remember might be as important as knowing what to forget. Welcome to the era of “sleeptime compute.” AI Summary and Description: Yes Summary: The text introduces the concept of “sleeptime compute,” which emphasizes…