Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion models/ai-in-browser.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

Artificial Intelligence (aka LLM) is getting added to everything, including the Web Browser, which will have some severe unanticipated downside for the user.

Contributor: Tom Jones 2024-09-27
Contributor: Tom Jones 2024-10-09

## Context

Expand Down Expand Up @@ -34,8 +34,15 @@ Given that the web is a fully open network, zero day vulnerabilities can be full

The supply chain that can be attacked includes the AI (LLM) module within the device. It is assumed that there may be multiple AI modules in the future, some of uncertain provenance. It is not at all clear why the browser API should trust the LLM provided.

**Cross-Site Attacks**

There is a current set of vulnerabilities for caching today that are being addressed by mitigations described in the feature listed below. Any cross-site vulnerability found there could equally apply to shared use of a user’s local AI not only within the browser but by any other app on the user’s device.

See the Feature: [Incorporating navigation initiator into the HTTP cache partition key](https://chromestatus.com/feature/5190577638080512)
and [the slide deck](https://docs.google.com/presentation/d/1StMrI1hNSw_QSmR7bg0w3WcIoYnYIt5K8G2fG01O0IA/edit#slide=id.g2f87bb2d5eb_0_4)
## Mitigations


**AI Isolation**

Only AI that has no interaction with the device holder may be accessed by any user agent that hosts pages from a web site that is not fully trusted by the holder or device owner. Specifically, the impact of the prompts entered by an origin site should not be able to impact either the holder or other origin site’s interactions with the holder.
Expand Down