{"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/out-of-the-cage-how-stochastic-parrots-win-in","title":"Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments","arxiv_id":"2308.12086","date":"2023-08-23","proceeding":null,"authors":["Maria Rigaki","Ondřej Lukáš","Carlos A. Catania","Sebastian Garcia"],"abstract":"Large Language Models (LLMs) have gained widespread popularity across diverse domains involving text generation, summarization, and various natural language processing tasks. Despite their inherent limitations, LLM-based designs have shown promising capabilities in planning and navigating open-world scenarios. This paper introduces a novel application of pre-trained LLMs as agents within cybersecurity network environments, focusing on their utility for sequential decision-making processes. We present an approach wherein pre-trained LLMs are leveraged as attacking agents in two reinforcement learning environments. Our proposed agents demonstrate similar or better performance against state-of-the-art agents trained for thousands of episodes in most scenarios and configurations. In addition, the best LLM agents perform similarly to human testers of the environment without any additional training process. This design highlights the potential of LLMs to efficiently address complex decision-making tasks within cybersecurity. Furthermore, we introduce a new network security environment named NetSecGame. The environment is designed to eventually support complex multi-agent scenarios within the network security domain. The proposed environment mimics real network attacks and is designed to be highly modular and adaptable for various scenarios.","url_abs":"https://arxiv.org/abs/2308.12086v2","url_pdf":"https://arxiv.org/pdf/2308.12086v2.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":"out-of-the-cage-how-stochastic-parrots-win-in","repo_url":"https://github.com/stratosphereips/netsecgame","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":null,"task_name":"CyberBattleSim"},{"task_slug":null,"task_name":"CyberBattleSim (RL) chain scenario"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":null,"task_name":"NetSecGame"},{"task_slug":null,"task_name":"NetSecGame (RL) full scenario defender"},{"task_slug":null,"task_name":"NetSecGame (RL) full scenario no defender"},{"task_slug":null,"task_name":"NetSecGame (RL) small scenario defender"},{"task_slug":null,"task_name":"NetSecGame (RL) small scenario no defender"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.12086","atlas_url":"https://app.syntology.ai/?focus=2308.12086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12086"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/stratosphereips/netsecgame","reach":{"status":"ok","spdx":"GPL-2.0"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"cec399377fc7664c","entry":"calculate_episode_lengths","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/utils/log_parser.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/utils/log_parser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"cec399377fc7664c"}},{"code_sha256_prefix":"4e431d7bdd56acdb","entry":"convert_msg_dict_to_json","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/game/coordinator.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/game/coordinator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4e431d7bdd56acdb"}},{"code_sha256_prefix":"dd9ed5e7cb747cfc","entry":"get_agent_color","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/utils/aidojo_log_colorizer.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/utils/aidojo_log_colorizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dd9ed5e7cb747cfc"}},{"code_sha256_prefix":"25ac25e66f7a03df","entry":"get_graph_stats","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/utils/gameplay_graphs.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/utils/gameplay_graphs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"25ac25e66f7a03df"}},{"code_sha256_prefix":"5e600efc7d8f6730","entry":"node_set","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/utils/gameplay_graphs.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/utils/gameplay_graphs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5e600efc7d8f6730"}},{"code_sha256_prefix":"dbed00960421ef6f","entry":"parse_actions_taken","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/utils/actions_parser.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/utils/actions_parser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dbed00960421ef6f"}},{"code_sha256_prefix":"3dd729de89e8cb21","entry":"reached_limit","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/utils/log_parser.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/utils/log_parser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3dd729de89e8cb21"}},{"code_sha256_prefix":"2a6015b6808c222b","entry":"sanitize_agent_name","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/game/coordinator.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/game/coordinator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2a6015b6808c222b"}},{"code_sha256_prefix":"db0eca0915234c88","entry":"process_line","repo":"stratosphereips/netsecgame","repo_kind":"official","path":"netsecgame/utils/aidojo_log_colorizer.py","file_url":"https://github.com/stratosphereips/netsecgame/blob/HEAD/netsecgame/utils/aidojo_log_colorizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"db0eca0915234c88"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}