paper-with-me

홈 › Papers

SafeGen: Embedding Ethical Safeguards in Text-to-Image Generation

2025-12-14 · Dang Phuong Nam, Nguyen Kieu, Pham Thanh Hieu arxiv

Generative Artificial Intelligence (AI) has created unprecedented opportunities for creative expression, education, and research. Text-to-image systems such as DALL.E, Stable Diffusion, and Midjourney can now convert ideas into visuals within seconds, but they also present a dual-use dilemma, raising critical ethical concerns: amplifying societal biases, producing high-fidelity disinformation, and violating intellectual property. This paper introduces SafeGen, a framework that embeds ethical safeguards directly into the text-to-image generation pipeline, grounding its design in established principles for Trustworthy AI. SafeGen integrates two complementary components: BGE-M3, a fine-tuned text classifier that filters harmful or misleading prompts, and Hyper-SD, an optimized diffusion model that produces high fidelity, semantically aligned images. Built on a curated multilingual (English- Vietnamese) dataset and a fairness-aware training process, SafeGen demonstrates that creative freedom and ethical responsibility can be reconciled within a single workflow. Quantitative evaluations confirm its effectiveness, with Hyper-SD achieving IS = 3.52, FID = 22.08, and SSIM = 0.79, while BGE-M3 reaches an F1-Score of 0.81. An ablation study further validates the importance of domain-specific fine-tuning for both modules. Case studies illustrate SafeGen's practical impact in blocking unsafe prompts, generating inclusive teaching materials, and reinforcing academic integrity.

📄 PDF Abstract BibTeX arXiv:2512.12501

Code (0)

등록된 구현이 없습니다.

Tasks

Text-to-Image Generation

Similar Papers 제목 키워드 기반

SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation

2026-05-31 · Yingzi Ma, Xiaogeng Liu, Yawen Zheng, Chaowei Xiao arxiv

With the rapid advancements in text-to-image diffusion models, generative video models (T2V models) like Sora can now produce short synthetic videos from a text prompt or an initial image. However, synthetic video genera…

Text-to-Video GenerationTemporal Sequences

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models

2024-04-10 · Xinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan 외

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 gene…

SafeGenes: Evaluating the Adversarial Robustness of Genomic Foundation Models

2025-06-01 · Huixin Zhan, Jason H. Moore

Genomic Foundation Models (GFMs), such as Evolutionary Scale Modeling (ESM), have demonstrated significant success in variant effect prediction. However, their adversarial robustness remains largely unexplored. To addres…

Adversarial Robustness

Applying Standards to Advance Upstream & Downstream Ethics in Large Language Models

2023-06-06 · Jose Berengueres, Marybeth Sandell

This paper explores how AI-owners can develop safeguards for AI-generated content by drawing from established codes of conduct and ethical standards in other content-creation industries. It delves into the current state …

BenchmarkingEthics

Beyond the Safeguards: Exploring the Security Risks of ChatGPT

2023-05-13 · Erik Derner, Kristina Batistič

The increasing popularity of large language models (LLMs) such as ChatGPT has led to growing concerns about their safety, security risks, and ethical implications. This paper aims to provide an overview of the different …

Code Generation