all InfoSec news
SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
April 11, 2024, 4:10 a.m. | Xinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan, Yanjiao Chen, Xiaoyu Ji, Wenyuan Xu
cs.CR updates on arXiv.org arxiv.org
Abstract: Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexual scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block explicit NSFW-related content (e.g., naked or sexy) but may still be vulnerable to adversarial prompts inputs that appear innocent but are …
arxiv countermeasures cs.ai cs.cl cs.cr cs.cv descriptions focus high image images inputs may nsfw performance quality safe stable diffusion text work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
Associate Manager, BPT Infrastructure & Ops (Security Engineer)
@ SC Johnson | PHL - Makati
Cybersecurity Analyst - Project Bound
@ NextEra Energy | Jupiter, FL, US, 33478
Lead Cyber Security Operations Center (SOC) Analyst
@ State Street | Quincy, Massachusetts
Junior Information Security Coordinator (Internship)
@ Garrison Technology | London, Waterloo, England, United Kingdom
Sr. Security Engineer
@ ScienceLogic | Reston, VA