Chrome Adds On-Device Gemini Nano While Ask Gemini Sends Page Content to Google Cloud
Google has added an AI on device toggle in Chrome settings that activates models running directly on the user's computer. The change supports several use cases, including detection of fraudulent websites. Several gigabytes of Gemini Nano weights now reside in the browser profile directory and execute on CPU or GPU.
Users might expect the downloaded model to power local features such as reading and summarizing the current page without cloud calls. However, Google chose a different approach. The company operates two separate systems under the single name Gemini.
Two Gemini Systems
Ask Gemini / Gemini in Chrome is a cloud service. When a user requests a summary or answers based on open tabs, the page content is sent to Google infrastructure. Gemini Nano is the local model downloaded by Chrome and invoked only through specialized browser APIs by websites, extensions, or the browser itself for initial checks.
- Ask Gemini / Gemini in Chrome – runs in Google cloud, invoked by the user
- Gemini Nano via built-in APIs – runs on the computer, invoked by sites and extensions
- Gemini Nano in Safe Browsing – performs primary analysis locally, invoked by Chrome
In the last case the model itself operates locally, yet with Enhanced Protection enabled its analysis results may be forwarded to Google Safe Browsing.
The Ask Gemini button in the interface triggers the cloud service. Page content and URLs are temporarily stored in the user's Google account, and with history saving enabled they appear in Gemini activity logs. Up to ten additional tabs shared by the user may also be processed in the cloud.
Related articles
WebRTC IP Leaks Explained: Why Disabling the Protocol Harms Anonymity in Anti-Detect Browsers
The article from Aurorium details how WebRTC technology can leak real IP addresses even when users route traffic through proxies. It explains the peer-to-peer mechanics of WebRTC, the role of STUN servers in generating ICE candidates, and why standard TCP proxies fail to handle UDP traffic. Disabling WebRTC via flags or JavaScript extensions creates detectable anomalies that anti-fraud systems flag as non-standard environments. The recommended approach involves native emulation inside the browser kernel so that STUN requests return proxy IPs while preserving full API integrity across workers. Additional leaks through local network addresses, mDNS candidates, and IPv6 are also covered with practical verification methods using tools like BrowserLeaks and CreepJS.
Docx Anonymizer: Open-Source Chrome Extension Uses Fine-Tuned rubert-tiny2 to Anonymize Personal Data Before AI Uploads
A Russian developer has released Docx Anonymizer, a browser extension that automatically detects and replaces personal data in documents using a lightweight NER model before they reach public AI services such as ChatGPT. The tool was created to help organizations comply with Russia’s 152-FZ personal data protection law while avoiding the risks of uploading contracts and other sensitive files to cloud-based LLMs. It runs entirely locally via ONNX Runtime and WebAssembly, requires no network calls, and supports any AI chat interface. The underlying model, rubert-tiny2, was further trained through knowledge distillation on WikiANN, factRuEval, and synthetic business documents, reaching strong F1 scores for person and organization entities after int8 quantization. The extension intercepts text on the fly, performs named-entity recognition in under two seconds for typical contracts, and replaces detected entities with placeholders. The project is fully open source and designed for minimal user friction, addressing the growing problem of employees inadvertently leaking corporate and personal data to public AI platforms.
Hybrid Post-Quantum Message Sealing: X25519 + ML-KEM-1024 in Umbera Messenger with Public Rust Tests
Umbera messenger has open-sourced its cryptographic core and published seven Rust tests that anyone can run to verify its hybrid post-quantum message sealing scheme. The design combines X25519 with ML-KEM-1024 so that an attacker must break both algorithms to decrypt a message. Messages are protected by Double Ratchet for forward secrecy, sealed sender packaging, and per-message ephemeral keys derived via HKDF-SHA256 into AES-256-GCM. The relay server stores only an opaque box identifier and encrypted blob with no sender or recipient fields visible. Media calls use DTLS-SRTP end-to-end while TURN servers see only encrypted datagrams. Addresses for message boxes rotate weekly and are derived solely from the shared secret between the two parties.
Free Ad Blocker for iPhone, Android, and Desktop Uses DNS Parsing Without Libraries and Skips YouTube Influencer Ads From the First Second
A new free ad-blocking solution has been released for iPhone, Android, and desktop platforms. The tool relies on a lightweight DNS parser that operates without external libraries. It includes a dedicated mode for users who already run VPN connections. An accompanying browser extension automatically skips sponsored segments in YouTube videos, even when the advertisement begins at the zero-second mark. The developer describes the technical challenges encountered after launch and the fixes applied to maintain compatibility across operating systems. The project emphasizes user privacy by avoiding unnecessary data collection and third-party dependencies.