Experimental News Clipping Site

Tag: authors

  • Hacker News: A Comprehensive Formal Security Analysis of OAuth 2.0

    —

    by

    Kurt Seifried
    in

    Source URL: https://arxiv.org/abs/1601.01229 Source: Hacker News Title: A Comprehensive Formal Security Analysis of OAuth 2.0 Feedly Summary: Comments AI Summary and Description: Yes Summary: The paper presents a comprehensive formal security analysis of the OAuth 2.0 protocol, a widely used authorization standard essential for secure single sign-on (SSO) applications. It highlights vulnerabilities discovered during analysis…

  • 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…

  • Google Online Security Blog: Securing tomorrow’s software: the need for memory safety standards

    —

    by

    Kurt Seifried
    in

    Source URL: http://security.googleblog.com/2025/02/securing-tomorrows-software-need-for.html Source: Google Online Security Blog Title: Securing tomorrow’s software: the need for memory safety standards Feedly Summary: AI Summary and Description: Yes Summary: The text discusses the critical issue of memory safety vulnerabilities and advocates for a shift towards secure-by-design practices to enhance overall security across the software industry. It emphasizes the…

  • 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: DeepDive in everything of Llama3: revealing detailed insights and implementation

    —

    by

    Kurt Seifried
    in

    Source URL: https://github.com/therealoliver/Deepdive-llama3-from-scratch Source: Hacker News Title: DeepDive in everything of Llama3: revealing detailed insights and implementation Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text details an in-depth exploration of implementing the Llama3 model from the ground up, focusing on structural optimizations, attention mechanisms, and how updates to model architecture enhance understanding…

  • Schneier on Security: Implementing Cryptography in AI Systems

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/02/implementing-cryptography-in-ai-systems.html Source: Schneier on Security Title: Implementing Cryptography in AI Systems Feedly Summary: Interesting research: “How to Securely Implement Cryptography in Deep Neural Networks.” Abstract: The wide adoption of deep neural networks (DNNs) raises the question of how can we equip them with a desired cryptographic functionality (e.g, to decrypt an encrypted input,…

  • Hacker News: Meta claims torrenting pirated books isn’t illegal without proof of seeding

    —

    by

    Kurt Seifried
    in

    Source URL: https://arstechnica.com/tech-policy/2025/02/meta-defends-its-vast-book-torrenting-were-just-a-leech-no-proof-of-seeding/ Source: Hacker News Title: Meta claims torrenting pirated books isn’t illegal without proof of seeding Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses Meta’s legal defense in response to allegations related to the illegal torrenting of copyrighted books for AI model training. It underscores the mounting tensions surrounding…

  • Cloud Blog: An SRE’s guide to optimizing ML systems with MLOps pipelines

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/devops-sre/applying-sre-principles-to-your-mlops-pipelines/ Source: Cloud Blog Title: An SRE’s guide to optimizing ML systems with MLOps pipelines Feedly Summary: Picture this: you’re an Site Reliability Engineer (SRE) responsible for the systems that power your company’s machine learning (ML) services. What do you do to ensure you have a reliable ML service, how do you know…