Feb. 7, 2024, 5:10 a.m. | Mohamed E. Hussein Sudharshan Subramaniam Janakiraman Wael AbdAlmageed

cs.CR updates on arXiv.org arxiv.org

Training machine learning models can be very expensive or even unaffordable. This may be, for example, due to data limitations (unavailability or being too large), or computational power limitations. Therefore, it is a common practice to rely on open-source pre-trained models whenever possible. However, this practice is alarming from a security perspective. Pre-trained models can be infected with Trojan attacks, in which the attacker embeds a trigger in the model such that the model's behavior can be controlled by the …

can computational cs.cr cs.cv cs.lg data detection large limitations machine machine learning machine learning models may optimization perspective power practice security training trojan

Deputy Chief Information Security Officer

@ United States Holocaust Memorial Museum | Washington, DC

Humbly Confident Security Lead

@ YNAB | Remote

Information Technology Specialist II: Information Security Engineer

@ WBCP, Inc. | Pasadena, CA.

Director of the Air Force Cyber Technical Center of Excellence (CyTCoE)

@ Air Force Institute of Technology | Dayton, OH, USA

Senior Cyber Security Analyst

@ Valley Water | San Jose, CA

Information Security Consultant- PAM

@ Eurofins | Bengaluru, India