CVE-2024-36323: Improper isolation of VCN-JPEG HW register space could allow a malicious Guest Virtual Machine (VM) or a pr...
Improper isolation of VCN-JPEG HW register space could allow a malicious Guest Virtual Machine (VM) or a process to perform unauthorized access to the register space of the JPEG cores assigned a victim VM/process, potentially gaining arbitrary read/write access to the victim VM/process data.
Security readout for executives and security teams
Plain-English summary
This AMD GPU issue weakens isolation around JPEG hardware registers. In the wrong local or virtualized setup, a malicious guest VM or local process could access data belonging to another VM or process. The business risk is highest where affected GPUs are shared across tenants, workloads, or trust boundaries.
Executive priority
Treat this as a high-priority infrastructure exposure where affected AMD GPUs support shared or isolated workloads. Standalone workstations are lower urgency than cloud, lab, AI, or virtualization hosts crossing trust boundaries.
Technical view
CVE-2024-36323 is an improper access control issue in VCN-JPEG hardware register isolation. The CVSS 4.0 score is 8.8 high. A local low-privileged attacker, with a required attack condition, may gain unauthorized register-space access and arbitrary read/write access to victim VM or process data.
Likely exposure
Exposure appears limited to systems using listed AMD Radeon RX 7000, Radeon PRO W7000, or Instinct MI300/MI325/MI308 products with the cited software or ROCm/ROC versions, especially GPU-sharing, passthrough, or multi-process environments.
Exploitation context
The provided sources do not show CISA KEV listing or confirmed active exploitation. The attack is local and relevant when an attacker can run a malicious guest VM or process near protected GPU workloads.
Researcher notes
The source bundle does not include exploit details, proof of active exploitation, or precise fixed-version mapping beyond AMD’s advisory reference. Validate exposure by product, driver stack, and isolation model before assigning operational risk.
Mitigation direction
Review AMD-SB-6027 for official remediation and corrected software guidance.
Prioritize remediation on shared GPU, VM, passthrough, and multi-tenant systems.
Restrict untrusted VM or process access to affected GPU JPEG resources where feasible.
Avoid treating GPU sharing as a strong isolation boundary until remediated.
Monitor AMD and CVE records for updated fixed-version details.
Validation and detection
Inventory systems with affected Radeon RX 7000, Radeon PRO W7000, and Instinct products.
Compare installed Radeon Software, PRO Edition, ROCm, or ROC versions with AMD-SB-6027.
Identify workloads using GPU sharing, VM passthrough, or tenant-separated GPU access.
Check whether affected hosts process sensitive data from multiple trust zones.
Track KEV status separately; the provided bundle marks KEV as false.
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Potential ATT&CK relevance
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
cwe · medium confidence lookup
CWE-284: Authorization and privilege behavior lookup
Authorization weaknesses can support privilege escalation and valid-account review, depending on exploit path. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
1CVSS vectors
3Timeline events
1ADP providers
2Source links
SSVC decision data
CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: noTechnical Impact: total
CVSS vector scores
1 official score
We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
CWE-284 · source CWE mapping
Improper Access Control
Improper Access Control represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.