{"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/targeted-attack-on-deep-rl-based-autonomous","title":"Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns","arxiv_id":"2109.07723","date":"2021-09-16","proceeding":null,"authors":["Prasanth Buddareddygari","Travis Zhang","Yezhou Yang","Yi Ren"],"abstract":"Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous driving. Threat models for these demonstrations are limited to (1) targeted attacks through real-time manipulation of the agent's observation, and (2) untargeted attacks through manipulation of the physical environment. The former assumes full access to the agent's states/observations at all times, while the latter has no control over attack outcomes. This paper investigates the feasibility of targeted attacks through visually learned patterns placed on physical objects in the environment, a threat model that combines the practicality and effectiveness of the existing ones. Through analysis, we demonstrate that a pre-trained policy can be hijacked within a time window, e.g., performing an unintended self-parking, when an adversarial object is present. To enable the attack, we adopt an assumption that the dynamics of both the environment and the agent can be learned by the attacker. Lastly, we empirically show the effectiveness of the proposed attack on different driving scenarios, perform a location robustness test, and study the tradeoff between the attack strength and its effectiveness. Code is available at https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","url_abs":"https://arxiv.org/abs/2109.07723v2","url_pdf":"https://arxiv.org/pdf/2109.07723v2.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":"targeted-attack-on-deep-rl-based-autonomous","repo_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.07723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07723"}},"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/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","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":"837d4eea1279559f","entry":"flatten_parameters","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"dynamics_model/misc.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/dynamics_model/misc.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":"837d4eea1279559f"}},{"code_sha256_prefix":"96d1dd75423bc8fe","entry":"get_perturbation_file_path","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"attacks/utils.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/attacks/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":"96d1dd75423bc8fe"}},{"code_sha256_prefix":"981e457f03f24f1d","entry":"get_target_state","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"attacks/utils.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/attacks/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":"981e457f03f24f1d"}},{"code_sha256_prefix":"bceda6b63b9938b0","entry":"loss_function","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"dynamics_model/trainvae.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/dynamics_model/trainvae.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":"bceda6b63b9938b0"}},{"code_sha256_prefix":"8569358964a0a9fd","entry":"read_loss_from_file","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"attacks/utils.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/attacks/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":"8569358964a0a9fd"}},{"code_sha256_prefix":"14b55062c4bf7192","entry":"rgb2gray","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"data_collection/carracing.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/data_collection/carracing.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":"14b55062c4bf7192"}},{"code_sha256_prefix":"a357513b1f5a499e","entry":"sample_continuous_policy","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"dynamics_model/misc.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/dynamics_model/misc.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":"a357513b1f5a499e"}},{"code_sha256_prefix":"b50053542050011a","entry":"unflatten_parameters","repo":"ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD","repo_kind":"official","path":"dynamics_model/misc.py","file_url":"https://github.com/ASU-APG/Targeted-Physical-Adversarial-Attacks-on-AD/blob/HEAD/dynamics_model/misc.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":"b50053542050011a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}