Experimental News Clipping Site

Tag: Malicious Use

  • NCSC Feed: From bugs to bypasses: adapting vulnerability disclosure for AI safeguards

    —

    by

    Kurt Seifried
    in

    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…

  • Slashdot: One Long Sentence is All It Takes To Make LLMs Misbehave

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/08/27/1756253/one-long-sentence-is-all-it-takes-to-make-llms-misbehave?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: One Long Sentence is All It Takes To Make LLMs Misbehave Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a significant security research finding from Palo Alto Networks’ Unit 42 regarding vulnerabilities in large language models (LLMs). The researchers explored methods that allow users to bypass…

  • The Register: First AI-powered ransomware spotted, but it’s not active – yet

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/26/first_aipowered_ransomware_spotted_by/ Source: The Register Title: First AI-powered ransomware spotted, but it’s not active – yet Feedly Summary: Oh, look, a use case for OpenAI’s gpt-oss-20b model ESET malware researchers Anton Cherepanov and Peter Strycek have discovered what they describe as the “first known AI-powered ransomware," which they named PromptLock. … AI Summary and Description:…

  • Slashdot: Commissioner of Canada Elections Will ‘Explore the Use’ of AI

    —

    by

    Kurt Seifried
    in

    Source URL: https://news.slashdot.org/story/25/08/14/1610236/commissioner-of-canada-elections-will-explore-the-use-of-ai?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Commissioner of Canada Elections Will ‘Explore the Use’ of AI Feedly Summary: AI Summary and Description: Yes Summary: The Office of the Commissioner of Canada Elections (OCCE) is exploring the use of AI and emerging technologies to enhance its operations and tackle electoral challenges. This initiative comes amid rising…

  • The Cloudflare Blog: Vulnerability disclosure on SSL for SaaS v1 (Managed CNAME)

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.cloudflare.com/vulnerability-disclosure-on-ssl-for-saas-v1-managed-cname/ Source: The Cloudflare Blog Title: Vulnerability disclosure on SSL for SaaS v1 (Managed CNAME) Feedly Summary: An upcoming vulnerability disclosure in Cloudflare’s SSL for SaaSv1 is detailed, explaining the steps we’ve taken towards deprecation. AI Summary and Description: Yes Summary: The text discusses a vulnerability discovered in Cloudflare’s SSL for SaaS v1…

  • The Register: At last, a use case for AI agents with high sky-high ROI: Stealing crypto

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/07/10/ai_agents_automatically_steal_cryptocurrency/ Source: The Register Title: At last, a use case for AI agents with high sky-high ROI: Stealing crypto Feedly Summary: Boffins outsmart smart contracts with evil automation Using AI models to generate exploits for cryptocurrency contract flaws appears to be a promising business model, though not necessarily a legal one.… AI Summary…