Researcher poisons open-weight AI model for under $100

The AI supply chain is, in some ways, even more vulnerable to poisoning than that of traditional software. Katie Paxton-Fear, ...

This experiment shows how easy it is to poison an open-weight AI model for under $100

A cybersecurity researcher poisoned an open weight AI model for under $100 in about an hour, exposing how easily these increasingly popular systems can be secretly compromised without detection.
Infosecurity Magazine

Phishing Campaign Hides Lua Loader as TrueType Font File

A large-scale phishing operation has been observed disguising a malicious script as a TrueType font file (.tff). Using the ...

‘I’m from a small Irish village – I manifested being in the world’s biggest TV show’

I’m from a really small village in Ireland called Laytown, in a county called Meath,’ he tells Metro.  ‘I remember seeing ...

Cursorに「リポジトリを開くだけ」で任意コードが実行される脆弱性、報告から7カ月たっても修正されず研究者が全容公開

AIを使ったプログラミング支援機能を備えるコードエディター「Cursor」のWindows版で、細工されたリポジトリを開くだけで任意のプログラムが自動実行される脆弱(ぜいじゃく)性が見つかりました。発見したAIセキュリティ企業のMindgardは20 ...