Scam & Threat Detection
On-device detectors that flag phishing, scams, and malicious messages or links.
熊猫吃短信 - 旧版
A category-defining on-device SMS spam filter that uses a Core ML model trained on hundreds of thousands of samples to semantically catch junk with zero manual rules, and famously never even requests network permission. Award-recognized with a strong 4.78 rating across 488 reviews, it's a gold standard for local Scam & Threat Detection.
- +Pure Core ML on-device classification, no rules and no network access at all
- +Award-winning with high ratings and a large review base
- +Genuinely private: never uploads message content
- −Legacy (older) version; superseded by the 2.0 release
- −$12.99 one-time and Chinese-SMS focused
熊猫吃短信2 - 垃圾短信拦截
The 2.0 successor to the panda SMS filter, using a new Core ML architecture for more accurate, finer-grained on-device classification (finance, orders, carrier, weather) while refusing cloud recognition. It's a top local Scam & Threat Detection pick, now free with a 4.62 rating over 233 reviews.
ScamNet: Anti-Scam Suite
A broad anti-scam suite that combines an offline SMS detection engine, on-device Apple Intelligence foundation-model checks, and proactive Safari/network/call shields, earning a strong 4.87 rating. It's a versatile pick for Scam & Threat Detection, though its deepest analysis and family features are cloud-based and subscription-gated.
Vigilant:Adult Content Blocker
FreeAccountability tool that detects explicit content on-screen in third-party apps and auto-blocks them; flags and blurs detections for later review. Rated 5/5 (21).
Slop Or Not - AI Detector
FreePrivately flags AI-generated text and deepfake images entirely on the Apple Neural Engine, with C2PA watermark checks and a text cleanup tool; nothing uploaded.
短信拦截 - 拒收垃圾短信防骚扰
$1.99Offline SMS filter that uses a Core ML model to block spam, scams and harassment locally, with whitelist/blacklist rules and zero network access.
SMS SPAM Filter
FreeRule-based SMS blocker with an offline AI evaluator that scores incoming messages entirely on-device, never transmitting your texts.
Maat
$0.49Safari trust layer that flags AI-generated text and rates source credibility/bias on every article using a Core ML classifier on the Neural Engine.
OrionShield
FreeOn-device security review that flags startup/threat signals and watches the clipboard for sensitive patterns, with a local AI posture assistant.
SentimentalMail
$0.99Apple Mail extension that analyzes message tone on-device, flagging emails positive/neutral/negative with colors and showing sentiment trends over time.
Spam Lucid
FreePrivacy-first call and SMS spam blocker using on-device heuristics and ML scoring to flag scam patterns, VoIP numbers, and risky links before they reach you.
Stormhood: AI Scam Detector
FreeAI scam and phishing detector that analyzes suspicious screenshots, text, and links, with local analysis where possible to protect privacy.
Stormhood
FreeScam guardian that locally optimizes screenshots of SMS/WhatsApp/email and analyzes messages and links for fraud, explaining the warning signs.
RedFox AI Phishing Defender
FreeReal-time phishing defender for Mac that flags malicious links across apps with on-screen warnings; the developer says all analysis happens locally.
Vigilant Browser Extension
FreeSafari companion that pipes web images and video frames to the Vigilant desktop app, where on-device AI flags explicit content for accountability reports.
ScamRadar Ai
FreeBrowser extension that flags scam patterns, fake urgency timers, and suspicious domains in real time, with privacy-first local scanning.
RedFox Check&Go
FreeFlags phishing SMS and dangerous links via the iOS Message Filter system using machine-learning models; on-device not explicitly stated.