Jan. 17, 2024, 1:17 p.m. | Kishalaya Kundu

TechSpot www.techspot.com


Tracked as CVE-2023-4969, the vulnerability allows attackers to recover data from GPU local memory. While it affects all GPU applications, it is especially dangerous for large language models (LLMs) and machine learning (ML) workloads that often process copious amounts of potentially sensitive data. By recovering local memory, the researchers claim...

Read Entire Article

ai data amd apple applications attackers cve data expose gpu gpus language language models large llms local machine machine learning memory new vulnerability process qualcomm recover sensitive sensitive data vulnerability workloads

Security Analyst

@ Northwestern Memorial Healthcare | Chicago, IL, United States

GRC Analyst

@ Richemont | Shelton, CT, US

Security Specialist

@ Peraton | Government Site, MD, United States

Information Assurance Security Specialist (IASS)

@ OBXtek Inc. | United States

Cyber Security Technology Analyst

@ Airbus | Bengaluru (Airbus)

Vice President, Cyber Operations Engineer

@ BlackRock | LO9-London - Drapers Gardens