Experimental News Clipping Site

Tag: insecure code

  • Slashdot: AI Code Generators Are Writing Vulnerable Software Nearly Half the Time, Analysis Finds

    —

    by

    Kurt Seifried
    in

    Source URL: https://developers.slashdot.org/story/25/07/30/150216/ai-code-generators-are-writing-vulnerable-software-nearly-half-the-time-analysis-finds?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: AI Code Generators Are Writing Vulnerable Software Nearly Half the Time, Analysis Finds Feedly Summary: AI Summary and Description: Yes Summary: The excerpt discusses alarming findings from Veracode’s 2025 GenAI Code Security Report, indicating significant security flaws in AI-generated code. Nearly 45% of the tested coding tasks showed vulnerabilities,…

  • CSA: Primer on Model Context Protocol (MCP) Implementation

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloudsecurityalliance.org/articles/a-primer-on-model-context-protocol-mcp-secure-implementation Source: CSA Title: Primer on Model Context Protocol (MCP) Implementation Feedly Summary: AI Summary and Description: Yes **Summary:** The text serves as a comprehensive implementation guide for deploying the Model Context Protocol (MCP) with a security-focused lens, emphasizing threat modeling using the MAESTRO framework. It offers practical insights into building secure Large…

  • The Register: ‘Ongoing’ Ivanti hijack bug exploitation reaches clouds

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/05/21/ivanti_rce_attacks_ongoing/ Source: The Register Title: ‘Ongoing’ Ivanti hijack bug exploitation reaches clouds Feedly Summary: Nothing like insecure code in security suites The “ongoing exploitation" of two Ivanti bugs has now extended beyond on-premises environments and hit customers’ cloud instances, according to security shop Wiz.… AI Summary and Description: Yes Summary: The text highlights…

  • Simon Willison’s Weblog: Demo of ChatGPT Code Interpreter running in o3-mini-high

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Mar/5/code-interpreter/ Source: Simon Willison’s Weblog Title: Demo of ChatGPT Code Interpreter running in o3-mini-high Feedly Summary: Demo of ChatGPT Code Interpreter running in o3-mini-high OpenAI made GPT-4.5 available to Plus ($20/month) users today. I was a little disappointed with GPT-4.5 when I tried it through the API, but having access in the ChatGPT…

  • Schneier on Security: “Emergent Misalignment” in LLMs

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/02/emergent-misalignment-in-llms.html Source: Schneier on Security Title: “Emergent Misalignment” in LLMs Feedly Summary: Interesting research: “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs“: Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model…

  • The Register: Does terrible code drive you mad? Wait until you see what it does to OpenAI’s GPT-4o

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/27/llm_emergent_misalignment_study/ Source: The Register Title: Does terrible code drive you mad? Wait until you see what it does to OpenAI’s GPT-4o Feedly Summary: Model was fine-tuned to write vulnerable software – then suggested enslaving humanity Computer scientists have found that fine-tuning notionally safe large language models to do one thing badly can negatively…

  • Simon Willison’s Weblog: Quoting Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/25/emergent-misalignment/ Source: Simon Willison’s Weblog Title: Quoting Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs Feedly Summary: In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding: it asserts…

  • Hacker News: Narrow finetuning can produce broadly misaligned LLM [pdf]

    —

    by

    Kurt Seifried
    in

    Source URL: https://martins1612.github.io/emergent_misalignment_betley.pdf Source: Hacker News Title: Narrow finetuning can produce broadly misaligned LLM [pdf] Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The document presents findings on the phenomenon of “emergent misalignment” in large language models (LLMs) like GPT-4o when finetuned on specific narrow tasks, particularly the creation of insecure code. The results…

  • Hacker News: Python’s official documentation contains textbook example of insecure code (XSS)

    —

    by

    Kurt Seifried
    in

    Source URL: https://seclists.org/fulldisclosure/2025/Feb/15 Source: Hacker News Title: Python’s official documentation contains textbook example of insecure code (XSS) Feedly Summary: Comments AI Summary and Description: Yes Summary: The text highlights a critical security issue within Python’s documentation related to Cross-Site Scripting (XSS) vulnerabilities stemming from examples in the CGI module. This poses significant risks for web…

  • CSA: DeepSeek 11x More Likely to Generate Harmful Content

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloudsecurityalliance.org/blog/2025/02/19/deepseek-r1-ai-model-11x-more-likely-to-generate-harmful-content-security-research-finds Source: CSA Title: DeepSeek 11x More Likely to Generate Harmful Content Feedly Summary: AI Summary and Description: Yes Summary: The text presents a critical analysis of the DeepSeek’s R1 AI model, highlighting its ethical and security deficiencies that raise significant concerns for national and global safety, particularly in the context of the…