{"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/balancing-detectability-and-performance-of","title":"Balancing detectability and performance of attacks on the control channel of Markov Decision Processes","arxiv_id":"2109.07171","date":"2021-09-15","proceeding":null,"authors":["Alessio Russo","Alexandre Proutiere"],"abstract":"We investigate the problem of designing optimal stealthy poisoning attacks on the control channel of Markov decision processes (MDPs). This research is motivated by the recent interest of the research community for adversarial and poisoning attacks applied to MDPs, and reinforcement learning (RL) methods. The policies resulting from these methods have been shown to be vulnerable to attacks perturbing the observations of the decision-maker. In such an attack, drawing inspiration from adversarial examples used in supervised learning, the amplitude of the adversarial perturbation is limited according to some norm, with the hope that this constraint will make the attack imperceptible. However, such constraints do not grant any level of undetectability and do not take into account the dynamic nature of the underlying Markov process. In this paper, we propose a new attack formulation, based on information-theoretical quantities, that considers the objective of minimizing the detectability of the attack as well as the performance of the controlled process. We analyze the trade-off between the efficiency of the attack and its detectability. We conclude with examples and numerical simulations illustrating this trade-off.","url_abs":"https://arxiv.org/abs/2109.07171v1","url_pdf":"https://arxiv.org/pdf/2109.07171v1.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":"balancing-detectability-and-performance-of","repo_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07171"}},"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/rssalessio/optimal-attack-control-channel-mdp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"779a5d41d9a6e05f","entry":"check_absolute_continuity","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"inventory_management_problem/utils.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/inventory_management_problem/utils.py","link_basis":"first_harvest_node","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":"779a5d41d9a6e05f"}},{"code_sha256_prefix":"eebcd520478da982","entry":"check_absolute_continuity_policies","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"inventory_management_problem/utils.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/inventory_management_problem/utils.py","link_basis":"first_harvest_node","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":"eebcd520478da982"}},{"code_sha256_prefix":"831b18395cc96105","entry":"compute_R","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"linear_system_example/utils.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/linear_system_example/utils.py","link_basis":"first_harvest_node","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":"831b18395cc96105"}},{"code_sha256_prefix":"0a88c9560abbc937","entry":"compute_deterministic_attack","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"inventory_management_problem/attacker.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/inventory_management_problem/attacker.py","link_basis":"first_harvest_node","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":"0a88c9560abbc937"}},{"code_sha256_prefix":"454a951272fcfec2","entry":"compute_power_series","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"linear_system_example/utils.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/linear_system_example/utils.py","link_basis":"first_harvest_node","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":"454a951272fcfec2"}},{"code_sha256_prefix":"92ea6eba414964df","entry":"compute_randomized_attack","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"inventory_management_problem/attacker.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/inventory_management_problem/attacker.py","link_basis":"first_harvest_node","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":"92ea6eba414964df"}},{"code_sha256_prefix":"ff64b94ebaf71f03","entry":"dlqr","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"linear_system_example/utils.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/linear_system_example/utils.py","link_basis":"first_harvest_node","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":"ff64b94ebaf71f03"}},{"code_sha256_prefix":"92644ea24d460ab0","entry":"value_iteration","repo":"rssalessio/optimal-attack-control-channel-mdp","repo_kind":"official","path":"inventory_management_problem/utils.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/inventory_management_problem/utils.py","link_basis":"first_harvest_node","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":"92644ea24d460ab0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}