In recent experiments, we found that GLM 5.3 can autonomously compromise recent versions of Mozilla Firefox using security fixes that have been published but not yet shipped to users. We used a deliberately basic setup meant to emulate a relatively unsophisticated attacker with limited resources. After basic initial instructions to inspect those not-yet-shipped fixes, the model reliably built successful exploits for six recent Firefox versions on its own using only information available at the time of release. These exploits, which cost about $1,000 per compromised version, would let an attacker steal passwords and authentication cookies stored in the browser, or read any files on the user's computer, after the user opens a single webpage, with no further interaction. The exploits make…Read original on X
StoryFirst seen
Epoch AI study finds GLM model can exploit unshipped Firefox security fixes
Security patches that are published but not yet delivered to users could be turned into working attacks with only a basic setup.
Everything it touches
0 names 1 voices 1 source posts
The story’s neighborhood
Explore the graph, or choose a connection below.
Follow the evidence
The source posts
This brief comes from Tech Twitter’s edited headlines. The posts below are the sources grouped with the story; statements in them belong to their authors.
How the headline evolved
Epoch AI study finds GLM model can exploit unshipped Firefox security fixes
Epoch AI study finds GLM model can exploit unshipped Firefox fixes
GLM 5.3 builds Firefox exploits from unreleased security fixes
Epoch AI test shows GLM 5.3 exploits unreleased Firefox security fixes
AI model turns unreleased Firefox security fixes into working exploits
AI model turns unreleased Firefox security fixes into working exploits