Hackers influence ChatGPT and Gemini to direct users to scam centers
Attackers poison ChatGPT, Gemini, and Google AI Overview with GEO-optimized fake content, steering users of 374 companies toward scam phone numbers and phishing pages.
A detection system analyzing AI answers found in-the-wild GEO (Generative Engine Optimization) poisoning campaigns affecting 374 companies, including Fortune 100 firms, major airlines (Delta, Lufthansa, Emirates), banks (Chase, Bank of America, Wells Fargo), and travel platforms. Attackers planted tens of thousands of malicious pages on UGC platforms (Tumblr, BuzzFeed, GitHub Pages, government/university file uploads) containing fake support numbers, emails, and login pages that ChatGPT, Gemini, and Google AI Overview cite as trusted answers. Poisoning is probabilistic, with higher-quality attacking content increasing the success rate, and operates at a scale traditional takedowns cannot match.
- 374 companies targeted, including Fortune 100, airlines, banks, and travel platforms
- Tens of thousands of GEO-optimized malicious pages on UGC platforms
- AI systems cite fake phone numbers, emails, and login pages as trusted answers
- Poisoning is statistical; better-crafted content raises the success rate
- ATT&CK
- T1606.002 Forge Web Credentials: Search Engine Optimization PoisoningT1566.002 Spearphishing Link
- AI models
- Gemini
Indicators of compromise
auto-extracted · verify before use · export allAll| Type | Indicator | Context |
|---|---|---|
| domain | raiselysite.com | rch, Event platforms — Posh.vip, onecause.com , bebee.com , raiselysite.com , and more Random websites abused for payload delivery — Ye |
| contact@vigilance.security | her or not your company is under attack, reach out to us at contact@vigilance.security . Reach out anytime We are Ariel Simon , Naor Haziz , Dan L |
From the original article
9 min read at medium.com
Think you can trust AI to give you correct answer? Think again. ChatGPT, Gemini, and Google AI Overview are being poisoned by a massive AI disinformation attack.
By ArielSimon · medium.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.