all AI news
Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples
March 11, 2024, 4:41 a.m. | Eda Yilmaz, Hacer Yalim Keles
cs.LG updates on arXiv.org arxiv.org
Abstract: Knowledge Distillation (KD) facilitates the transfer of discriminative capabilities from an advanced teacher model to a simpler student model, ensuring performance enhancement without compromising accuracy. It is also exploited for model stealing attacks, where adversaries use KD to mimic the functionality of a teacher model. Recent developments in this domain have been influenced by the Stingy Teacher model, which provided empirical analysis showing that sparse outputs can significantly degrade the performance of student models. Addressing …
abstract accuracy advanced adversarial adversarial examples arxiv attacks capabilities cs.cr cs.cv cs.lg defense distillation examples knowledge performance stealing transfer type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US