all InfoSec news
Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks
April 2, 2024, 7:12 p.m. | Mingwen Shao, Lingzhuang Meng, Yuanjian Qiao, Lixu Zhang, Wangmeng Zuo
cs.CR updates on arXiv.org arxiv.org
Abstract: Since the training data of the target model is not available in the black-box substitute attack, most recent schemes utilize GANs to generate data for training the substitute model. However, these GANs-based schemes suffer from low training efficiency as the generator needs to be retrained for each target model during the substitute training process, as well as low generation quality. To overcome these limitations, we consider utilizing the diffusion model to generate data, and propose …
arxiv attacks augmentation code cs.cr cs.cv cs.lg data free stable diffusion
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information System Security Officer / Auditor
@ Peraton | Washington, DC, United States
Senior Cloud Security Engineer
@ Alludo | US | Boston, MA, US | San Francisco, CA, US | Austin, TX, US
Tier 3 - Malware Analyst, SME
@ Resource Management Concepts, Inc. | Quantico, Virginia, United States
Temp to Hire Senior DevSecOps Engineer
@ Scientific Systems Company, Inc. | Burlington, Massachusetts, United States
Security Engineer III - Splunk | SIEM
@ JPMorgan Chase & Co. | Plano, TX, United States
Information Systems Security Officer / Auditor
@ Peraton | Washington, DC, United States