SEC536: Adversarial AI - Penetration Testing AI Systems


Experience SANS training through course previews.
Learn MoreLet us help.
Contact usBecome a member for instant access to our free resources.
Sign UpWe're here to help.
Contact UsQR Code detection engines in email security solutions suffer from a common problem: the most commonly used method for decoding QR Codes is simple and predictable. By exploiting the decoding algorithm and leveraging existing QR data-layering techniques, this research provides the security industry with a working proof-of-concept to bypass email security gateway detection systems. This method is also effective against mobile applications, such as camera and QR Code applications, as well as open-source libraries used to decode QR Codes.
Furthermore, the proposed technique does not require the attacker to hide the QR Code from automated detection; instead, it presents the malicious payload in plain sight, masquerading as a legitimate QR Code containing a benign URL. Recommendations to detect and prevent this attack vector include context simulation and visual AI analysis.





















