Passepartout, VPN Client
GRATUIT
Free
Utilities
Free
SpamGuard: AI Spam Filter
by Furkan ERKORKMAZ
Description
Block 99% of SMS spam, smishing, and brand-impersonation scams in 33 languages — fully on-device. Your messages never leave your phone.
SpamGuard runs Apple's Message Filter Extension to catch spam, scams, and phishing the moment they arrive. No setup, no waiting, no servers.
WHY SPAMGUARD
- On-device AI that filters spam in milliseconds
- Privacy-first: your messages never leave your device by default
- Brand-impersonation detector: catches "Apple ID alert at apple-id-secure.xyz"
- 33-language coverage with locale-aware keyword packs
- Custom keyword and sender rules for full control
- Multi-category sorting: spam, scam, promotion, transaction
- Confidence-based filtering to minimize false positives
DEFEATS EVASION TRICKS
- Catches leetspeak: fr33b3t, g00gle, paypa1
- Strips zero-width and invisible characters scammers hide in URLs
- Detects punycode and lookalike domains: paypa1.com, аpple.com (Cyrillic а)
- Sees through RTL-override and percent-encoding obfuscation
- Reverses fragmented keywords like "f.r.e.e.b.e.t"
33 LANGUAGES, ONE FILTER
SpamGuard recognizes the language of each incoming message and applies a curated keyword pack — from English, Spanish, Portuguese, French, German, Italian, Dutch, Turkish, Polish, Russian, Arabic, Hebrew, Persian, Hindi, Bengali, Indonesian, Malay, Vietnamese, Thai, Tagalog, Japanese, Korean, simplified and traditional Chinese, Greek, Czech, Romanian, Hungarian, Swedish, Danish, Norwegian, Finnish, and Ukrainian. No competitor filters spam content this broadly.
HOW IT WORKS
SpamGuard integrates directly with the Messages app through Apple's Message Filter Extension. When a text arrives from an unknown sender, SpamGuard's AI analyzes it instantly on your device and moves spam to the junk folder automatically. No action needed.
AI-POWERED DETECTION
- Machine learning model trained on thousands of real spam messages
- Detects lottery scams, package delivery fraud, crypto schemes, and phishing links
- Burst-rate tracker flags unknown senders messaging at campaign frequency
- Confidence-based filtering minimizes false positives and protects real messages
CUSTOM RULES
- Create your own block and allow lists
- Filter by keyword, sender, phone number, or pattern
- Priority-based rule processing — your rules always come first
LEARNS FROM YOU
Tap "mark as spam" or "not spam" on any filtered message and SpamGuard biases future verdicts from the same sender accordingly. Your feedback never leaves your device.
PRO PACK
- Server AI for maximum spam detection accuracy on the toughest messages
- Unlimited custom rules
- Smart multi-category message sorting
- Category customization and mapping
- Time-based filtering schedules
- Priority support
GET STARTED
1. Download and enable SpamGuard in Settings > Messages > Unknown & Spam
2. Spam filtering starts automatically — no setup required
3. Fine-tune with custom rules anytime in the app
PRIVACY FIRST
SpamGuard processes messages locally using on-device machine learning. Sender feedback and burst-rate tracking use SHA256-hashed identifiers and never leave your device. If you enable optional Server AI (Pro Pack), message text from unknown senders is sent to our server for classification only — never stored after processing. Privacy is not a feature. It is a right.
Terms of Use: https://audioartai.com/terms
Privacy Policy: https://audioartai.com/privacy
Support: https://audioartai.com/support/
SpamGuard runs Apple's Message Filter Extension to catch spam, scams, and phishing the moment they arrive. No setup, no waiting, no servers.
WHY SPAMGUARD
- On-device AI that filters spam in milliseconds
- Privacy-first: your messages never leave your device by default
- Brand-impersonation detector: catches "Apple ID alert at apple-id-secure.xyz"
- 33-language coverage with locale-aware keyword packs
- Custom keyword and sender rules for full control
- Multi-category sorting: spam, scam, promotion, transaction
- Confidence-based filtering to minimize false positives
DEFEATS EVASION TRICKS
- Catches leetspeak: fr33b3t, g00gle, paypa1
- Strips zero-width and invisible characters scammers hide in URLs
- Detects punycode and lookalike domains: paypa1.com, аpple.com (Cyrillic а)
- Sees through RTL-override and percent-encoding obfuscation
- Reverses fragmented keywords like "f.r.e.e.b.e.t"
33 LANGUAGES, ONE FILTER
SpamGuard recognizes the language of each incoming message and applies a curated keyword pack — from English, Spanish, Portuguese, French, German, Italian, Dutch, Turkish, Polish, Russian, Arabic, Hebrew, Persian, Hindi, Bengali, Indonesian, Malay, Vietnamese, Thai, Tagalog, Japanese, Korean, simplified and traditional Chinese, Greek, Czech, Romanian, Hungarian, Swedish, Danish, Norwegian, Finnish, and Ukrainian. No competitor filters spam content this broadly.
HOW IT WORKS
SpamGuard integrates directly with the Messages app through Apple's Message Filter Extension. When a text arrives from an unknown sender, SpamGuard's AI analyzes it instantly on your device and moves spam to the junk folder automatically. No action needed.
AI-POWERED DETECTION
- Machine learning model trained on thousands of real spam messages
- Detects lottery scams, package delivery fraud, crypto schemes, and phishing links
- Burst-rate tracker flags unknown senders messaging at campaign frequency
- Confidence-based filtering minimizes false positives and protects real messages
CUSTOM RULES
- Create your own block and allow lists
- Filter by keyword, sender, phone number, or pattern
- Priority-based rule processing — your rules always come first
LEARNS FROM YOU
Tap "mark as spam" or "not spam" on any filtered message and SpamGuard biases future verdicts from the same sender accordingly. Your feedback never leaves your device.
PRO PACK
- Server AI for maximum spam detection accuracy on the toughest messages
- Unlimited custom rules
- Smart multi-category message sorting
- Category customization and mapping
- Time-based filtering schedules
- Priority support
GET STARTED
1. Download and enable SpamGuard in Settings > Messages > Unknown & Spam
2. Spam filtering starts automatically — no setup required
3. Fine-tune with custom rules anytime in the app
PRIVACY FIRST
SpamGuard processes messages locally using on-device machine learning. Sender feedback and burst-rate tracking use SHA256-hashed identifiers and never leave your device. If you enable optional Server AI (Pro Pack), message text from unknown senders is sent to our server for classification only — never stored after processing. Privacy is not a feature. It is a right.
Terms of Use: https://audioartai.com/terms
Privacy Policy: https://audioartai.com/privacy
Support: https://audioartai.com/support/
What's new (v1.1)
Major filter rebuild — SpamGuard now defends against the latest SMS scam tricks in 33 languages.
NEW
• Brand-impersonation detector catches "Apple ID alert at apple-id-secure.xyz" patterns across 35+ brands.
• 33-language keyword packs with on-device language detection.
• Defeats evasion: leetspeak ("fr33b3t"), zero-width characters, punycode lookalikes ("paypa1.com"), RTL-override URLs, percent-encoded TLDs, fragmented keywords ("f.r.e.e.b.e.t").
• Sender burst-rate tracker flags unknown senders messaging at campaign frequency.
• Mark as spam / not spam — feedback adjusts future verdicts automatically.
FASTER & SAFER
• Atomic counter file for cross-process accuracy.
• Reset Filter Memory: granular controls for activity, feedback, rate, and statistics.
• Activity preview is now opt-in — only senders and verdicts are kept by default.
• Hashed sender identifiers never leave your device.
UNDER THE HOOD
• Swift actor-based data layer for safer concurrency.
• 230 unit and integration tests across 19 locales.
• Privacy manifest updated to declare every data type accurately.
NEW
• Brand-impersonation detector catches "Apple ID alert at apple-id-secure.xyz" patterns across 35+ brands.
• 33-language keyword packs with on-device language detection.
• Defeats evasion: leetspeak ("fr33b3t"), zero-width characters, punycode lookalikes ("paypa1.com"), RTL-override URLs, percent-encoded TLDs, fragmented keywords ("f.r.e.e.b.e.t").
• Sender burst-rate tracker flags unknown senders messaging at campaign frequency.
• Mark as spam / not spam — feedback adjusts future verdicts automatically.
FASTER & SAFER
• Atomic counter file for cross-process accuracy.
• Reset Filter Memory: granular controls for activity, feedback, rate, and statistics.
• Activity preview is now opt-in — only senders and verdicts are kept by default.
• Hashed sender identifiers never leave your device.
UNDER THE HOOD
• Swift actor-based data layer for safer concurrency.
• 230 unit and integration tests across 19 locales.
• Privacy manifest updated to declare every data type accurately.
