{"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/fast-and-low-cost-genomic-foundation-models","title":"Fast and Low-Cost Genomic Foundation Models via Outlier Removal","arxiv_id":"2505.00598","date":"2025-05-01","proceeding":null,"authors":["Haozheng Luo","Chenghao Qiu","Maojiang Su","Zhihan Zhou","Zoe Mehta","Guo Ye","Jerry Yao-Chieh Hu","Han Liu"],"abstract":"We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GERM. Unlike existing GFM benchmarks, GERM offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologically, we evaluate the adversarial robustness of five state-of-the-art GFMs using four widely adopted attack algorithms and three defense strategies. Importantly, our benchmark provides an accessible and comprehensive framework to analyze GFM vulnerabilities with respect to model architecture, quantization schemes, and training datasets. Empirically, transformer-based models exhibit greater robustness to adversarial perturbations compared to HyenaDNA, highlighting the impact of architectural design on vulnerability. Moreover, adversarial attacks frequently target biologically significant genomic regions, suggesting that these models effectively capture meaningful sequence features.","url_abs":"https://arxiv.org/abs/2505.00598v1","url_pdf":"https://arxiv.org/pdf/2505.00598v1.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":"fast-and-low-cost-genomic-foundation-models","repo_url":"https://github.com/MAGICS-LAB/GERM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"dna-analysis","task_name":"DNA analysis"},{"task_slug":"genome-understanding","task_name":"Genome Understanding"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"splice-site-prediction","task_name":"Splice Site Prediction"},{"task_slug":"transcription-factor-binding-site-prediction-1","task_name":"Transcription Factor Binding Site Prediction (Human)"},{"task_slug":"transcription-factor-binding-site-prediction-2","task_name":"Transcription Factor Binding Site Prediction (Mouse)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.00598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00598"}},"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":"deterministic:regex_extraction","url":"https://github.com/MAGICS-LAB/GERM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"12c35a5891d87be1","entry":"generate_kmer_str","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"evaluation/validate_nt.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/evaluation/validate_nt.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12c35a5891d87be1"}},{"code_sha256_prefix":"e6b562614d5aa421","entry":"get_alter_of_dna_sequence","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"evaluation/validate_nt.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/evaluation/validate_nt.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e6b562614d5aa421"}},{"code_sha256_prefix":"1586b639a5abd0b0","entry":"init_to_zero","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"DNABERT2/flash_attn_triton.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/DNABERT2/flash_attn_triton.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1586b639a5abd0b0"}},{"code_sha256_prefix":"49d5adb77f62eba3","entry":"to_bytes","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"FT/DNABERT-2-FT/finetune/cnt_para.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/FT/DNABERT-2-FT/finetune/cnt_para.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49d5adb77f62eba3"}},{"code_sha256_prefix":"a41fa8c40b551ec1","entry":"unpad_input_only","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"DNABERT2/bert_padding.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/DNABERT2/bert_padding.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a41fa8c40b551ec1"}},{"code_sha256_prefix":"0477d55df4c9ce2a","entry":"attach_act_hooks","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"evaluation/validate_nt.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/evaluation/validate_nt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0477d55df4c9ce2a"}},{"code_sha256_prefix":"e40f7b6dc5c3977a","entry":"get_human_readable_count","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"FT/DNABERT-2-FT/finetune/cnt_para.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/FT/DNABERT-2-FT/finetune/cnt_para.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e40f7b6dc5c3977a"}},{"code_sha256_prefix":"1de20a7e07a6fb60","entry":"load_or_generate_kmer","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"FT/DNABERT-2-FT/finetune/train2.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/FT/DNABERT-2-FT/finetune/train2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1de20a7e07a6fb60"}},{"code_sha256_prefix":"b166dc11d0f54137","entry":"pad_input","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"DNABERT2/bert_padding.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/DNABERT2/bert_padding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b166dc11d0f54137"}},{"code_sha256_prefix":"ee341a843ab02d5f","entry":"unpad_input","repo":"MAGICS-LAB/GERM","repo_kind":"official","path":"DNABERT2/bert_padding.py","file_url":"https://github.com/MAGICS-LAB/GERM/blob/HEAD/DNABERT2/bert_padding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee341a843ab02d5f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}