Automated Recognition Mechanism with Inadequate Detection or Handling of Adversarial Input Perturbations

The product uses an automated mechanism such as machine learning to recognize complex data inputs (e.g. image or audio) as a particular concept or category, but it does not properly detect or handle inputs that have been modified or constructed in a way that causes the mechanism to detect a different, incorrect concept.

CVEs (3)

CVE VENDORS PRODUCTS UPDATED PUBLISHED CVSS
CVE-2025-3578 - - Jun 17, 2026 Apr 15, 2025 9.3 CRITICAL· v4 N/A· v3 N/A· v2 A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environme...Show more A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments. In addition, it would be possible to cause bugs that would result in the exfiltration of sensitive information, such as details about the software or internal system paths. These actions could be carried out through the misuse of LLM Prompt (chatbot) technology, via the /api/<string-chat>/message endpoint, by manipulating the contents of the ‘content’ parameter.Show less
CVE-2025-26644 1Microsoft 8Windows 10 1809 Windows 10 21h2Windows 10 22h2+5 more Jun 17, 2026 Apr 8, 2025 N/A· v4 5.1 MEDIUM· v3 N/A· v2 Automated recognition mechanism with inadequate detection or handling of adversarial input perturbations in Windows Hello allows an unauthorized attacker to perform spoofing locally.
CVE-2023-20071 1Cisco 4Cyber Vision Firepower Threat DefenseMeraki Mx Security Appliance Firmware+1 more Jun 17, 2026 Nov 1, 2023 N/A· v4 5.8 MEDIUM· v3 N/A· v2 Multiple Cisco products are affected by a vulnerability in the Snort detection engine that could allow an unauthenticated, remote attacker to bypass the configured policies on an affected system. This vulnerability is du...Show more Multiple Cisco products are affected by a vulnerability in the Snort detection engine that could allow an unauthenticated, remote attacker to bypass the configured policies on an affected system. This vulnerability is due to a flaw in the FTP module of the Snort detection engine. An attacker could exploit this vulnerability by sending crafted FTP traffic through an affected device. A successful exploit could allow the attacker to bypass FTP inspection and deliver a malicious payload.Show less