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, Thursday 4 July 2024 Retrospective Covers 3 July 2024 00:00 to 4 July 2024 00:00 UTC Web: https://keryn.dev/headlines/daily/2024-07-04/ TOP DEVELOPMENTS [1] “Everything’s frozen”: Ransomware locks credit union users out of bank accounts Ars Technica: Security · Incident · https://arstechnica.com/tech-policy/2024/07/everythings-frozen-ransomware-locks-credit-union-users-out-of-bank-accounts [2] Formula 1 governing body discloses data breach after email hacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/formula-1-governing-body-discloses-data-breach-after-email-hacks [3] 384,000 sites pull code from sketchy code library recently bought by Chinese firm Ars Technica: Security · Research · https://arstechnica.com/security/2024/07/384000-sites-link-to-code-library-caught-performing-supply-chain-attack [4] Chainguard Enhances Security With OSV Advisory Feed OpenSSF · Advisory · https://openssf.org/blog/2024/07/03/chainguard-enhances-security-with-osv-advisory-feed [5] Microsoft MSHTML Flaw Exploited to Deliver MerkSpy Spyware Tool The Hacker News · Incident · https://thehackernews.com/2024/07/microsoft-mshtml-flaw-exploited-to.html SCA [6] NIST’s role in enhancing software supply chain security Chainguard · Standard / policy · https://chainguard.dev/unchained/nists-role-in-enhancing-software-supply-chain-security REMEDIATION [7] JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets arXiv · Research · https://arxiv.org/abs/2407.03045 MODELS [8] Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning arXiv · Research · https://arxiv.org/abs/2407.03391 [9] SOS! Soft Prompt Attack Against Open-Source Large Language Models arXiv · Research · https://arxiv.org/abs/2407.03160 [10] From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks arXiv · Research · https://arxiv.org/abs/2407.02855 ADVISORIES IN THIS WINDOW 10 npm advisories · 10 critical 1 Maven advisory · 1 high 1 Go advisory · 1 critical 1 RubyGems advisory · 1 moderate 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.