src_d11443da85ea659d49
- Source-provided label
- Not reported
- Evidence class
- mentioned in report
- Confidence
- Not reported
- Observed
- Nov 12, 2024 00:00 UTC
- Retrieved
- Oct 08, 2026 03:52 UTC
ModeLeak: LLM Model Exfiltration Vulnerability in Vertex AI
A vulnerability in GCP's Vertex AI service allows privilege escalation and unauthorized access to sensitive LLM models. Attackers can exfiltrate these models by exploiting misconfigurations in access controls and service bindings. By exploiting custom job permissions, researchers were able to escalate their privileges and gain unauthorized access to all data services in the project. In addition, d
Reference details
- Source category
- Research & news
- Report title
ModeLeak: LLM Model Exfiltration Vulnerability in Vertex AI- First reported
- Nov 12, 2024 00:00 UTC
- Last reported
- Nov 12, 2024 00:00 UTC
- Catalog updated
- Oct 08, 2026 03:52 UTC
- Record ID
0678649a9cbc1e7a090866749f3a33384b338a95ec8aaa8399df03c60e1d3230
Published indicators
Network indicators are visibly defanged. This page does not make them clickable or send them to another service.
No validated file hashes or network indicators are stored for this record.
Source observations
This record contains metadata and attribution only. It does not host, download, unpack, render, or execute malware samples.
Feed collection status
Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.
1 sources: 0 stale, 0 needing attention, 0 paused, 1 unverified.
Review source update dates and status
- src_d11443da85ea659d49Collection status unverifiedLast successful batch: Unverified
Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.