Experimental News Clipping Site

Tag: malicious behavior

  • The Register: When AI is trained for treachery, it becomes the perfect agent

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/09/29/when_ai_is_trained_for/ Source: The Register Title: When AI is trained for treachery, it becomes the perfect agent Feedly Summary: We’re blind to malicious AI until it hits. We can still open our eyes to stopping it Opinion Last year, The Register reported on AI sleeper agents. A major academic study explored how to train…

  • The Register: Perplexity vexed by Cloudflare’s claims its bots are bad

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/05/perplexity_vexed_by_cloudflares_claims/ Source: The Register Title: Perplexity vexed by Cloudflare’s claims its bots are bad Feedly Summary: AI search biz insists its content capture and summarization is okay because someone asked for it AI search biz Perplexity claims that Cloudflare has mischaracterized its site crawlers as malicious bots and that the content delivery network…

  • Anchore: Beyond Software Dependencies: The Data Supply Chain Security Challenge of AI-Native Applications

    —

    by

    Kurt Seifried
    in

    Source URL: https://anchore.com/blog/beyond-software-dependencies-the-data-supply-chain-security-challenge-of-ai-native-applications/ Source: Anchore Title: Beyond Software Dependencies: The Data Supply Chain Security Challenge of AI-Native Applications Feedly Summary: Just as the open source software revolution fundamentally transformed software development in the 2000s—bringing massive productivity gains alongside unprecedented supply chain complexity—we’re witnessing history repeat itself with Large Language Models (LLMs). The same pattern that…

  • Simon Willison’s Weblog: Agentic Misalignment: How LLMs could be insider threats

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jun/20/agentic-misalignment/#atom-everything Source: Simon Willison’s Weblog Title: Agentic Misalignment: How LLMs could be insider threats Feedly Summary: Agentic Misalignment: How LLMs could be insider threats One of the most entertaining details in the Claude 4 system card concerned blackmail: We then provided it access to emails implying that (1) the model will soon be…

  • Schneier on Security: Regulating AI Behavior with a Hypervisor

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/04/regulating-ai-behavior-with-a-hypervisor.html Source: Schneier on Security Title: Regulating AI Behavior with a Hypervisor Feedly Summary: Interesting research: “Guillotine: Hypervisors for Isolating Malicious AIs.” Abstract:As AI models become more embedded in critical sectors like finance, healthcare, and the military, their inscrutable behavior poses ever-greater risks to society. To mitigate this risk, we propose Guillotine, a…

  • Hacker News: Fake VS Code Extension on NPM Spreads Multi-Stage Malware

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.mend.io/blog/fake-vs-code-extension-on-npm-spreads-multi-stage-malware/ Source: Hacker News Title: Fake VS Code Extension on NPM Spreads Multi-Stage Malware Feedly Summary: Comments AI Summary and Description: Yes Summary: The text reports on a recent discovery of a malicious VS-code extension that employs typosquatting tactics to deliver multi-stage malware to unsuspecting developers. The incident highlights critical security vulnerabilities in…