PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address. KERYN HEADLINES Daily, Wednesday 24 April 2024 Retrospective Covers 23 April 2024 00:00 to 24 April 2024 00:00 UTC Web: https://keryn.dev/headlines/daily/2024-04-24/ TOP DEVELOPMENTS [1] The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions Simon Willison · Research · https://simonwillison.net/2024/Apr/23/the-instruction-hierarchy [2] Russia's APT28 Exploited Windows Print Spooler Flaw to Deploy 'GooseEgg' Malware The Hacker News · Incident · https://thehackernews.com/2024/04/russias-apt28-exploited-windows-print.html [3] Apache Cordova App Harness Targeted in Dependency Confusion Attack The Hacker News · Research · https://thehackernews.com/2024/04/apache-cordova-app-harness-targeted-in.html SAST [4] Vul-LMGNNs: Fusing language models and online-distilled graph neural networks for code vulnerability detection arXiv · Research · https://arxiv.org/abs/2404.14719 SCA [5] Webinar: Learn Proactive Supply Chain Threat Hunting Techniques The Hacker News · Analysis · https://thehackernews.com/2024/04/webinar-learn-proactive-supply-chain.html REMEDIATION [6] Microsoft pulls fix for Outlook bug behind ICS security alerts BleepingComputer · Analysis · https://bleepingcomputer.com/news/microsoft/microsoft-pulls-fix-for-outlook-bug-unexpected-ICS-warnings-after-December-security-updates [7] Microsoft releases Exchange hotfixes for security update issues BleepingComputer · Analysis · https://bleepingcomputer.com/news/microsoft/microsoft-releases-exchange-hotfixes-for-security-update-issues TRUST [8] AI Procurement Checklists: Revisiting Implementation in the Age of AI Governance arXiv · Research · https://arxiv.org/abs/2404.14660 MODELS [9] Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models arXiv · Research · https://arxiv.org/abs/2404.15236 [10] Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models arXiv · Research · https://arxiv.org/abs/2404.14795 [11] Simple probes can catch sleeper agents Anthropic · Analysis · https://anthropic.com/research/probes-catch-sleeper-agents ADVISORIES IN THIS WINDOW 7 npm advisories · 4 critical · 1 high · 2 moderate 2 Packagist advisories · 2 critical 2 Go advisories · 1 moderate · 1 low 2 PyPI advisories · 2 moderate 1 Maven advisory · 1 critical All advisories: https://keryn.dev/headlines/advisories/ Titles, links and short excerpts only; every item links to its source. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.