Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913745605754880 |
|---|---|
| author | Ying, Zonghao Zheng, Guangyi Huang, Yongxin Zhang, Deyue Zhang, Wenxin Zou, Quanchen Liu, Aishan Liu, Xianglong Tao, Dacheng |
| author_facet | Ying, Zonghao Zheng, Guangyi Huang, Yongxin Zhang, Deyue Zhang, Wenxin Zou, Quanchen Liu, Aishan Liu, Xianglong Tao, Dacheng |
| contents | This study presents the first comprehensive safety evaluation of the DeepSeek models, focusing on evaluating the safety risks associated with their generated content. Our evaluation encompasses DeepSeek's latest generation of large language models, multimodal large language models, and text-to-image models, systematically examining their performance regarding unsafe content generation. Notably, we developed a bilingual (Chinese-English) safety evaluation dataset tailored to Chinese sociocultural contexts, enabling a more thorough evaluation of the safety capabilities of Chinese-developed models. Experimental results indicate that despite their strong general capabilities, DeepSeek models exhibit significant safety vulnerabilities across multiple risk dimensions, including algorithmic discrimination and sexual content. These findings provide crucial insights for understanding and improving the safety of large foundation models. Our code is available at https://github.com/NY1024/DeepSeek-Safety-Eval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15092 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings Ying, Zonghao Zheng, Guangyi Huang, Yongxin Zhang, Deyue Zhang, Wenxin Zou, Quanchen Liu, Aishan Liu, Xianglong Tao, Dacheng Cryptography and Security Artificial Intelligence Computation and Language This study presents the first comprehensive safety evaluation of the DeepSeek models, focusing on evaluating the safety risks associated with their generated content. Our evaluation encompasses DeepSeek's latest generation of large language models, multimodal large language models, and text-to-image models, systematically examining their performance regarding unsafe content generation. Notably, we developed a bilingual (Chinese-English) safety evaluation dataset tailored to Chinese sociocultural contexts, enabling a more thorough evaluation of the safety capabilities of Chinese-developed models. Experimental results indicate that despite their strong general capabilities, DeepSeek models exhibit significant safety vulnerabilities across multiple risk dimensions, including algorithmic discrimination and sexual content. These findings provide crucial insights for understanding and improving the safety of large foundation models. Our code is available at https://github.com/NY1024/DeepSeek-Safety-Eval. |
| title | Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.15092 |