Experimental News Clipping Site

Tag: sequence

  • The Register: 30-year-old NHS supply chain system hit by 35 major alerts in 11 months

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/27/thirtyyearold_nhs_supply_chain_system/ Source: The Register Title: 30-year-old NHS supply chain system hit by 35 major alerts in 11 months Feedly Summary: Thousands of order lines not picked, causing delays to hospital deliveries A state-owned company that handles £4.5 billion ($5.7 billion) annual spending on behalf of the NHS has suffered 35 high-priority computer system…

  • The Register: Wallbleed vulnerability unearths secrets of China’s Great Firewall 125 bytes at a time

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/27/wallbleed_vulnerability_great_firewall/ Source: The Register Title: Wallbleed vulnerability unearths secrets of China’s Great Firewall 125 bytes at a time Feedly Summary: Boffins poked around inside censorship engines for years before Beijing patched hole Smart folks investigating a memory-dumping vulnerability in the Great Firewall of China (GFW) finally released their findings after probing it for…

  • The Register: Signal will withdraw from Sweden if encryption-busting laws take effect

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/26/signal_will_withdraw_from_sweden/ Source: The Register Title: Signal will withdraw from Sweden if encryption-busting laws take effect Feedly Summary: Experts warned the UK’s recent ‘victory’ over Apple would kickstart something of a domino effect Signal CEO Meredith Whittaker says her company will withdraw from countries that force messaging providers to allow law enforcement officials to…

  • 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…

  • CSA: Global ICS Exposures: State of the Internet Report

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloudsecurityalliance.org/articles/global-ics-exposures-what-our-state-of-the-internet-report-reveals-about-critical-infrastructure-security Source: CSA Title: Global ICS Exposures: State of the Internet Report Feedly Summary: AI Summary and Description: Yes Summary: The text discusses critical vulnerabilities within Industrial Control Systems (ICS), particularly focusing on the exposure of Human-Machine Interfaces (HMIs) that pose significant security risks. With many HMIs lacking robust security measures and connected…

  • The Register: Malware variants that target operational tech systems are very rare – but 2 were found last year

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/02/25/new_ics_malware_dragos/ Source: The Register Title: Malware variants that target operational tech systems are very rare – but 2 were found last year Feedly Summary: Fuxnet and FrostyGoop were both used in the Russia-Ukraine war Two new malware variants specifically designed to disrupt critical industrial processes were set loose on operational technology networks last…

  • Wired: Anthropic Launches the World’s First ‘Hybrid Reasoning’ AI Model

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.wired.com/story/anthropic-world-first-hybrid-reasoning-ai-model/ Source: Wired Title: Anthropic Launches the World’s First ‘Hybrid Reasoning’ AI Model Feedly Summary: Claude 3.7, the latest model from Anthropic, can be instructed to engage in a specific amount of reasoning to solve hard problems. AI Summary and Description: Yes Summary: The text discusses Claude 3.7, a new model from Anthropic,…

  • Hacker News: Grok 3 is highly vulnerable to indirect prompt injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/23/grok-3-indirect-prompt-injection/ Source: Hacker News Title: Grok 3 is highly vulnerable to indirect prompt injection Feedly Summary: Comments AI Summary and Description: Yes Summary: The text highlights significant vulnerabilities in xAI’s Grok 3 related to indirect prompt injection attacks, especially in the context of its operation on Twitter (X). This raises critical security concerns…

  • 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,…