{"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/provable-defense-against-backdoor-policies-in","title":"Provable Defense against Backdoor Policies in Reinforcement Learning","arxiv_id":"2211.10530","date":"2022-11-18","proceeding":null,"authors":["Shubham Kumar Bharti","Xuezhou Zhang","Adish Singla","Xiaojin Zhu"],"abstract":"We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact allows hidden triggers. During deployment, the adversary can modify observed states in a particular way to trigger unexpected actions and harm the agent. We assume the agent does not have the resources to re-train a good policy. Instead, our defense mechanism sanitizes the backdoor policy by projecting observed states to a 'safe subspace', estimated from a small number of interactions with a clean (non-triggered) environment. Our sanitized policy achieves $\\epsilon$ approximate optimality in the presence of triggers, provided the number of clean interactions is $O\\left(\\frac{D}{(1-\\gamma)^4 \\epsilon^2}\\right)$ where $\\gamma$ is the discounting factor and $D$ is the dimension of state space. Empirically, we show that our sanitization defense performs well on two Atari game environments.","url_abs":"https://arxiv.org/abs/2211.10530v1","url_pdf":"https://arxiv.org/pdf/2211.10530v1.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":"provable-defense-against-backdoor-policies-in","repo_url":"https://github.com/skbharti/provable-defense-in-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.10530","atlas_url":"https://app.syntology.ai/?focus=2211.10530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10530"}},"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/skbharti/provable-defense-in-rl","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"359d01d7827f0361","entry":"SanitizedPolicyGenerator","repo":"skbharti/provable-defense-in-rl","repo_kind":"official","path":"boxing_ram/trojai_rl/subspace_sanitize/policy_generator.py","file_url":"https://github.com/skbharti/provable-defense-in-rl/blob/HEAD/boxing_ram/trojai_rl/subspace_sanitize/policy_generator.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":"359d01d7827f0361"}},{"code_sha256_prefix":"4dd2ed0780ceefdd","entry":"load_clean_samples","repo":"skbharti/provable-defense-in-rl","repo_kind":"official","path":"boxing_ram/trojai_rl/subspace_sanitize/subspace_sanitization.py","file_url":"https://github.com/skbharti/provable-defense-in-rl/blob/HEAD/boxing_ram/trojai_rl/subspace_sanitize/subspace_sanitization.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4dd2ed0780ceefdd"}},{"code_sha256_prefix":"9586ba1db1bedeaf","entry":"sanitize_and_test_for_single_clean_batch","repo":"skbharti/provable-defense-in-rl","repo_kind":"official","path":"boxing_ram/trojai_rl/subspace_sanitize/subspace_sanitization.py","file_url":"https://github.com/skbharti/provable-defense-in-rl/blob/HEAD/boxing_ram/trojai_rl/subspace_sanitize/subspace_sanitization.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9586ba1db1bedeaf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}