{"url":"/task/computer-security","name":"Computer Security","slug":"computer-security","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":66,"papers_with_code":18,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/computer-security-on-big-bench","slug":"computer-security-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy "],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=5)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/ollabench-v-0-2","name":"OllaBench v.0.2","full_name":"OllaBench for Interdependent Cybersecurity v.0.2","num_papers_in_archive":1}],"subtasks":[{"url":"/task/file-type-identification","name":"File Type Identification"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":18,"of":18,"tagged_in_all":66,"items":[{"url":"/paper/novel-feature-extraction-selection-and-fusion","title":"Novel Feature Extraction, Selection and Fusion for Effective Malware Family Classification","date":"2015-11-13","arxiv_id":"1511.04317","repositories_listed":19,"syntology":null},{"url":"/paper/defending-against-neural-fake-news","title":"Defending Against Neural Fake News","date":"2019-05-29","arxiv_id":"1905.12616","repositories_listed":4,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":10}},{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/more-than-you-ve-asked-for-a-comprehensive","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","date":"2023-02-23","arxiv_id":"2302.12173","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/dont-paint-it-black-white-box-explanations","title":"Evaluating Explanation Methods for Deep Learning in Security","date":"2019-06-05","arxiv_id":"1906.02108","repositories_listed":2,"syntology":null},{"url":"/paper/active-anomaly-detection-via-ensembles-1","title":"Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning","date":"2019-01-23","arxiv_id":"1901.08930","repositories_listed":2,"syntology":{"n":21,"n_ran":0,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/active-anomaly-detection-via-ensembles","title":"Active Anomaly Detection via Ensembles","date":"2018-09-17","arxiv_id":"1809.06477","repositories_listed":2,"syntology":null},{"url":"/paper/reservoir-of-diverse-adaptive-learners-and","title":"Reservoir of Diverse Adaptive Learners and Stacking Fast Hoeffding Drift Detection Methods for Evolving Data Streams","date":"2017-09-07","arxiv_id":"1709.02457","repositories_listed":2,"syntology":null},{"url":"/paper/emergent-misalignment-narrow-finetuning-can","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","date":"2025-02-24","arxiv_id":"2502.17424","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/cysecbench-generative-ai-based-cybersecurity","title":"CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models","date":"2025-01-02","arxiv_id":"2501.01335","repositories_listed":1,"syntology":null},{"url":"/paper/secqa-a-concise-question-answering-dataset","title":"SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security","date":"2023-12-26","arxiv_id":"2312.15838","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/understand-waiting-time-in-transaction-fee","title":"Understand Waiting Time in Transaction Fee Mechanism: An Interdisciplinary Perspective","date":"2023-05-04","arxiv_id":"2305.02552","repositories_listed":1,"syntology":null},{"url":"/paper/sok-explainable-machine-learning-for-computer","title":"SoK: Explainable Machine Learning for Computer Security Applications","date":"2022-08-22","arxiv_id":"2208.10605","repositories_listed":1,"syntology":null},{"url":"/paper/cvss-bert-explainable-natural-language","title":"CVSS-BERT: Explainable Natural Language Processing to Determine the Severity of a Computer Security Vulnerability from its Description","date":"2021-11-16","arxiv_id":"2111.08510","repositories_listed":1,"syntology":null},{"url":"/paper/fragments-expert-a-graphical-user-interface-1","title":"Fragments Expert A Graphical User Interface MATLAB Toolbox for Classification of File Fragments","date":"2020-12-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/codecmr-cross-modal-retrieval-for-function","title":"CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/robust-neural-malware-detection-models-for","title":"Robust Neural Malware Detection Models for Emulation Sequence Learning","date":"2018-06-28","arxiv_id":"1806.10741","repositories_listed":1,"syntology":null},{"url":"/paper/neural-network-based-graph-embedding-for","title":"Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection","date":"2017-08-22","arxiv_id":"1708.06525","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}