ThreatCluster

Researchers Poison Stolen Data to Sabotage AI Model Accuracy

First seen 8 Jan 2026, 10:52 UTC • •40

Article Content

1 / 3

Browse articles

ThreatCluster •March 12, 2026 at 13:27 UTC

Researchers from the Chinese Academy of Sciences and Nanyang Technological University have developed a framework called AURA to protect knowledge graphs in GraphRAG systems from theft. By adulterating these graphs with fake but plausible data, the framework aims to render stolen copies ineffective for attackers, thereby ensuring the integrity of proprietary information.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Answers cite the sources they use

Updated 212d ago How this analysis works

More articles in this cluster (2)

Threat Graph

2 entities, 1 inferred relationships (STIX 2.1).

The full threat graph for this incident is free in the 7-day Starter trial.

Create free account

No card · 30 seconds

See everything included

Technique (2)

Data Breach
Malware

Relationships

Data Breach related to Malware

Continue Reading

CVE-2015-3306 Exploited in ProFTPD FTP Servers CVE-2015-3306, a vulnerability in ProFTPD 1.3.5, allows remote attackers to read and write arbitrary files using the SITE CPFR and SITE CPTO commands. This exploit can lead to unauthorized access and potential remote code execution, as the commands are executed with the privileges of the ProFTPD service. Active…

CISA Mandates Urgent Patching of Five Critical Flaws Exploited by Flax Typhoon The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has ordered federal agencies to patch five critical vulnerabilities by October 11, 2026, following exploitation by the China-linked hacking group Flax Typhoon. The vulnerabilities, added to CISA's Known Exploited Vulnerabilities (KEV) catalog, include…