{"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/dataset-and-lessons-learned-from-the-2024","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","arxiv_id":"2406.07954","date":"2024-06-12","proceeding":null,"authors":["Edoardo Debenedetti","Javier Rando","Daniel Paleka","Silaghi Fineas Florin","Dragos Albastroiu","Niv Cohen","Yuval Lemberg","Reshmi Ghosh","Rui Wen","Ahmed Salem","Giovanni Cherubin","Santiago Zanella-Beguelin","Robin Schmid","Victor Klemm","Takahiro Miki","Chenhao Li","Stefan Kraft","Mario Fritz","Florian Tramèr","Sahar Abdelnabi","Lea Schönherr"],"abstract":"Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt. The competition was organized in two phases. In the first phase, teams developed defenses to prevent the model from leaking the secret. During the second phase, teams were challenged to extract the secrets hidden for defenses proposed by the other teams. This report summarizes the main insights from the competition. Notably, we found that all defenses were bypassed at least once, highlighting the difficulty of designing a successful defense and the necessity for additional research to protect LLM systems. To foster future research in this direction, we compiled a dataset with over 137k multi-turn attack chats and open-sourced the platform.","url_abs":"https://arxiv.org/abs/2406.07954v1","url_pdf":"https://arxiv.org/pdf/2406.07954v1.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":"dataset-and-lessons-learned-from-the-2024","repo_url":"https://github.com/ethz-spylab/ctf-satml24-data-analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07954"}},"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/ethz-spylab/ctf-satml24-data-analysis","reach":{"status":"ok"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"e2e19a70f482c025","entry":"filter_empty_chats","repo":"ethz-spylab/ctf-satml24-data-analysis","repo_kind":"official","path":"raw_data_manipulation/filter_chats.py","file_url":"https://github.com/ethz-spylab/ctf-satml24-data-analysis/blob/HEAD/raw_data_manipulation/filter_chats.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2e19a70f482c025"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}