CWE-1448
Weaknesses Related to AI/ML Products
2026-04-27 +00:00
Notifikasi untuk CWE tertentu
Tetap terinformasi tentang perubahan untuk CWE tertentu.
Nama: Weaknesses Related to AI/ML Products
CWE entries in this view (graph) are unique to AI/ML products, or are commonly encountered in products that use or support AI/ML.
Anggota CWE
CWE-1446: Weaknesses That are Specific to AI/ML Technology Kategori
CWE-1447: General Software Weaknesses that Appear in Products that Use or Support AI/ML Technology Kategori
Informasi Tampilan CWE
Catatan Pemetaan Kerentanan
Justifikasi : This entry is a View. Views are not weaknesses and therefore inappropriate to describe the root causes of vulnerabilities.Komentar : Use this View or other Views to search and navigate for the appropriate weakness.
Catatan
This view is likely to be updated frequently in future versions. See Research Gaps.As of CWE 4.20, it is still difficult to distinguish common AI/ML related attacks from the underlying weaknesses. The CWE AI Working Group has had many discussions about this general topic. Much of the latest research has focused on the attacks, and/or characterizing the underlying design and implementation of AI/ML related systems. From a CWE perspective, the distinction between "control" and "data" is not necessarily as deep as currently considered within the AI/ML community, since most weaknesses are characterized in terms of potentially insecure "behavior" - whether that behavior occurred due to design, insecure code, insecure configuration, or data-driven behaviors such as AI/ML. Since AI/ML is frequently derived from repositories of software that consume AI/ML components - many public reports of AI/ML vulnerabilities ultimately result from commonly-occurring weaknesses that appear in most kinds of software. There are several weakness-focused research efforts within the industry, but these efforts are still in the early stages.
Audiens
| Pemangku kepentingan | Deskripsi |
|---|---|
| Software Developers | This view outlines the most important issues for developers who are using or adopting AI/ML. |
| Product Customers | This view outlines the most important issues that provide product customers with a way of asking their software development teams to follow minimum expectations for secure code. |
| Educators | Since AI/ML is a growing influence within industry, this view could provide educators and students with a focused set of weaknesses to learn about first. |
| Academic Researchers | Academic researchers could consult the "Research Gaps" notes to consider potential research opportunities for weakness-focused research. |
Pengajuan
| Nama | Organisasi | Tanggal | Tanggal rilis | Version |
|---|---|---|---|---|
| CWE Content Team | MITRE | 4.20 |
Referensi
REF-1522
Software Must Be Secure by Design, and Artificial Intelligence Is No ExceptionChristine Lai, Jonathan Spring.
https://www.cisa.gov/news-events/news/software-must-be-secure-design-and-artificial-intelligence-no-exception
REF-1523
AI Systems Are Software SystemsJonathan Spring.
https://www.first.org/conference/vulncon26/program#pAI-Systems-Are-Software-Systems
REF-1525
CVE ID Assignment and CVE Record Publication for AI-Related VulnerabilitiesCVE Program.
https://www.cve.org/Media/News/item/blog/2025/02/18/CVE-ID-CVE-Record-AIrelated-Vulnerabilities
