
AI AdBlocker (for Android) di eye3
AI AdBlocker for Firefox Android. Build using background scripts (no service worker) Blocks obvious ad containers + simple heuristics; no remote calls. Bundles ONNX Runtime Web locally(WASM only); no CDN, No data collection, no telemetry.
Cualchi funzion e podarès jessi a paiamentCualchi funzion e podarès jessi a paiament
Disponibil su Firefox par Androidâ˘Disponibil su Firefox par Androidâ˘
1 utent1 utent
Metadâts de estension
Schermadis



Informazions su la estension
No user data is collected, stored, or transmitted. No remote endpoints. All ML/WASM runs entirely locally.
This add-on is a starter AI Ad Block extension.
⢠The uploaded .zip is the Firefox-compatible build (no rules/ directory, uses background.scripts instead of service_worker).
⢠The uploaded source .zip contains the full, human-readable source code (TypeScript, scripts, manifests, build files) without dist/ or node_modules/.
⢠No remote code execution, dynamic code generation, or obfuscated code is used.
⢠Can detect hidden ads, sponsored labels, promoted posts, native ads that rule-based systems miss.
⢠Can adapt better if you re-train the model with new data.
Example AI Features You Can Add DOM / Heuristic Classifier:
Train a lightweight ML model on HTML snippets (features: tag type, attributes, text like âSponsoredâ).
Content script grabs candidate nodes â runs model â hide if classified as ad.
Vision-based Ad Detection:
Use a small CNN (e.g., MobileNet/ONNX quantized) to check if an <img> looks like a banner ad.
Useful for âimage-onlyâ ads where markup doesnât give them away.
Hybrid (most practical):
Use heuristics to filter likely candidates (divs with fixed size, suspicious classes, âsponsoredâ text).
Use ML to confirm â avoid false positives.
Future-proofing: when advertisers obfuscate HTML/CSS, rules break â but your ML model still generalizes.
Privacy-preserving: everything runs locally in the browser; no need to send page data to servers.
Research value: positions your extension as ânext-genâ ad blocker, different from commodity ones.
This add-on is a starter AI Ad Block extension.
⢠The uploaded .zip is the Firefox-compatible build (no rules/ directory, uses background.scripts instead of service_worker).
⢠The uploaded source .zip contains the full, human-readable source code (TypeScript, scripts, manifests, build files) without dist/ or node_modules/.
⢠No remote code execution, dynamic code generation, or obfuscated code is used.
⢠Can detect hidden ads, sponsored labels, promoted posts, native ads that rule-based systems miss.
⢠Can adapt better if you re-train the model with new data.
Example AI Features You Can Add DOM / Heuristic Classifier:
Train a lightweight ML model on HTML snippets (features: tag type, attributes, text like âSponsoredâ).
Content script grabs candidate nodes â runs model â hide if classified as ad.
Vision-based Ad Detection:
Use a small CNN (e.g., MobileNet/ONNX quantized) to check if an <img> looks like a banner ad.
Useful for âimage-onlyâ ads where markup doesnât give them away.
Hybrid (most practical):
Use heuristics to filter likely candidates (divs with fixed size, suspicious classes, âsponsoredâ text).
Use ML to confirm â avoid false positives.
Future-proofing: when advertisers obfuscate HTML/CSS, rules break â but your ML model still generalizes.
Privacy-preserving: everything runs locally in the browser; no need to send page data to servers.
Research value: positions your extension as ânext-genâ ad blocker, different from commodity ones.
Valutât 0 di 0 recensôrs
Permès e dâtsPlui informazions
Permès obligatoris:
- Acedi ai tiei dâts di ducj i sÎts web
Altris informazions
- Colegaments component adizionâl
- Version
- 0.1.6
- Dimension
- 107,82 kB
- Ultin inzornament
- 2 moannen lyn (19 aug. 2025)
- Categoriis coreladis
- Licence
- Licence MIT
- Informative su la riservatece
- Lei la informative su la riservatece par chest component adizionâl
- Cronologjie versions
- Etichetis
- Zonte ae racuelte
Il svilupadôr di cheste estension ti domande di sostignÎlu tal so disvilup continuatÎf fasint une piçule donazion.
It does not collect or transmit user data.
Reviewers can build the extension from source using the included scripts (see README).