{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-understanding-the-safety-boundaries","title":"Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings","arxiv_id":"2503.15092","date":"2025-03-19","proceeding":null,"authors":["Zonghao Ying","Guangyi Zheng","Yongxin Huang","Deyue Zhang","Wenxin Zhang","Quanchen Zou","Aishan Liu","Xianglong Liu","DaCheng Tao"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2503.15092v1","url_pdf":"https://arxiv.org/pdf/2503.15092v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-understanding-the-safety-boundaries","repo_url":"https://github.com/ny1024/deepseek-safety-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.15092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15092"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ny1024/deepseek-safety-eval","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"618e93855f6e4e2b","entry":"clean_text","repo":"ny1024/deepseek-safety-eval","repo_kind":"official","path":"eval/base/deepseek_r1.py","file_url":"https://github.com/ny1024/deepseek-safety-eval/blob/HEAD/eval/base/deepseek_r1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"618e93855f6e4e2b"}},{"code_sha256_prefix":"866c7b26066ee5ea","entry":"generate_prompt","repo":"ny1024/deepseek-safety-eval","repo_kind":"official","path":"judge/text/gpt4o_chinese.py","file_url":"https://github.com/ny1024/deepseek-safety-eval/blob/HEAD/judge/text/gpt4o_chinese.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"866c7b26066ee5ea"}},{"code_sha256_prefix":"30d1ee7bb73c4e61","entry":"query_model","repo":"ny1024/deepseek-safety-eval","repo_kind":"official","path":"eval/base/deepseek_r1.py","file_url":"https://github.com/ny1024/deepseek-safety-eval/blob/HEAD/eval/base/deepseek_r1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30d1ee7bb73c4e61"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}