履歴書100通に1通「AIだけが読める文字」 20万件調査でわかった“就活ハック”の手口 米研究
ITmedia AI+ja
ITmedia AI+
AI Global Wire米ノースカロライナ大学チャペルヒル校、米デューク大学、米UCバークレーなどに所属する研究者らがセキュリティ分野の国際会議「USENIX Security Symposium 2026」で発表した論文「Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening」は、AIをだます隠し文字入りの履歴書が現実の就職活動でどれほどまん延しているかを調査した研究報告だ。
This is a short summary published by AI Global Wire. The full article is owned and hosted by ITmedia AI+ — open it there to read it in full.
Read the full story at ITmedia AI+Related AI news
- Anthropic is setting up a "presidential engagement" program for the 2028 US elections that will offer AI policy education to candidates in both parties (Emily Forlini/Fortune)Techmeme · October 9, 2026
- Fem nycklar till att hålla tokenkostnaden under kontrollComputer Sweden · October 9, 2026
- Tämä on uusi internet – "Kone on aika armoton käyttäjä"Tivi · October 9, 2026
- Chinese developer makes ARTEX AI agent closed-source after Korean bank hackEconomic Times Tech · October 9, 2026
- Meta donates 1,000 AI glasses, $30k in SingaporeTech in Asia · October 9, 2026
- Google Cloud introduces Gemini agent for work as AI race heats upEconomic Times Tech · October 9, 2026