CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

CVE-2026-21400 identifies a protection mechanism failure in Intel(R) AI Reference Models before version v3.4.1 when operating in Ring 3 (User Applications). The issue could allow an escalation of privilege where an unprivileged software adversary, with a privileged user and low attack complexity,...

EUVD-2026-56516

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

PT-2026-70325

Name of the Vulnerable Software and Affected Versions IntelR AI Reference Models versions prior to v3.4.1 Description A protection mechanism failure within Ring 3 the least privileged level of the CPU architecture allows an unprivileged software adversary to escalate privileges. This issue can be...

Intel® AI Reference Models Software Advisory

Summary: A potential security vulnerability for some Intel® AI Reference Models software may allow escalation of privilege. Intel is releasing software updates to mitigate this potential vulnerability. Vulnerability Details: CVEID: CVE-2026-21400 Description: Protection mechanism failure for some...

CVE-2026-21400: Protection Mechanism Failure

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models

State-of-the-art membership inference attacks MIAs typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models LLMs. As a result, prior research has either relied on weaker attacks that avoid training reference models e.g.,...