Add use case on “Content Filtering” in WebNN specifications

[humeranoor]

Proposal Name: Add use case on “Content Filtering” in WebNN specifications

Currently, there is a gap when it comes to web standards for supporting content blocking and filtering. With this proposal, we suggest to add content filtering as a use case in the webNN specifications.

Short description

(Moving the original PR from webNN repository to the more general proposals repo.)

We at eyeo have been working on machine learning (ML)-based content filtering and have pioneered the use of ML in ad filtering. As discussed in the issue previously, we highlighted that there is a gap when it comes to web standards for supporting content blocking and filtering. This hinders in implementing solutions that upholds the W3C ethical principle that "People should be able to render web content as they want".

Hence we propose to add a use case on “Content Filtering” to existing use cases: https://webmachinelearning.github.io/webnn/#use cases-application

Example use cases

ML-based content filtering can be applied to a number of use cases like intrusive ad filtering, user privacy protection, cyber bullying detection and avoidance, clean-page user experience for specially-abled users.

A rough idea or two about implementation

We propose to add a use case in webNN specs as follows:

Content Filtering

A user is cautious about her online privacy and wants to be protected from the online trackers, malware and any third-parties present on the web pages that she visits. The ML-based content-filter [REF] identifies and blocks the third party content, while allowing her to safely surf her favorite websites. Thus she is safe and more in control of her online experience [REF2].

[REF] Ad-blocking: A Study on Performance, Privacy and Counter-measures
[REF2] Point [2.12] of the W3C Ethical Web Principles

With this proposal, we submit the use case on "Content Filtering" for addition to the WebNN specs. Having this use case in the specs will allow us as the web community to not only allow implementation of ML-based content filtering but also influence the shaping of web extensions and discuss improvements to APIs such as webRequest and declarativeNetRequest.

Looking forward to next steps.

Please let me know if you have any questions or comments.

Thanks,
Humera
h.minhas@eyeo.com

cc: @anssiko

[anssiko]

Thank you @humeranoor! I'll add this proposal to the next call agenda and will point people to this repo to solicit further feedback.

[humeranoor]

Awesome, Looking forward to the call.
Thanks a lot.

[humeranoor]

Thank you @anssiko for the discussion and positive reviews on the PR.
However, I feel a bit lost at this point. You recommended me to continue the discussion in the WebExtensions Community Group and introduce the proposal for APIs such as webRequest and declarativeNetRequest.

However, the purpose of my proposal is not to get these APIs in the first place. Our point of view is that first we should have a use case documented in the webNN-specs on "Content Filtering". As per our previous discussions, this is indeed an important use case and having it in the specifications will then allow us to make a case and impact the other APIs.

So, I see creating a PR to update the specs as a more appropriate first step. Don't you think so?

[anssiko]

@humeranoor, thanks for raising this. Let me try to explain in more detail how the case-driven approach to specification development works in the W3C Web Machine Learning WG and its incubator CG.

The WebNN specification work kicked off with identification of an initial set of use cases. These use cases were chosen by their popularity but most importantly considering implementation feasibility, more*. Technical scope of the API is evaluated against these use cases.

(*Other considerations include performance (can this run on a mainstream device with good UX?), external deps (can this be implemented now, any external API gaps?), privacy, security and ethics, etc.)

Forward-looking use cases that do not yet meet these requirements are discussed in the proposals repo. From time to time the WG evaluates the submitted forward-looking use cases in this repo to assess whether they're ready to be incorporated in the scope of the WebNN API.

Reaching consensus in the WebExt CG on the APIs content filtering use case depends on is an important step.