{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VJOSICXYT774Y4H4NINFSQD2FF","short_pith_number":"pith:VJOSICXY","schema_version":"1.0","canonical_sha256":"aa5d240af89fffcc70fc6a1a59407a29422f62d30e6c51770a3977bf7cd5d10b","source":{"kind":"arxiv","id":"2005.07099","version":1},"attestation_state":"computed","paper":{"title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Jianwen Sun, Kangjie Chen, Lei Ma, Tianwei Zhang, Xiaofei Xie, Yang Liu, Yan Zheng","submitted_at":"2020-05-14T16:06:38Z","abstract_excerpt":"Adversarial attacks against conventional Deep Learning (DL) systems and algorithms have been widely studied, and various defenses were proposed. However, the possibility and feasibility of such attacks against Deep Reinforcement Learning (DRL) are less explored. As DRL has achieved great success in various complex tasks, designing effective adversarial attacks is an indispensable prerequisite towards building robust DRL algorithms. In this paper, we introduce two novel adversarial attack techniques to \\emph{stealthily} and \\emph{efficiently} attack the DRL agents. These two techniques enable a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2005.07099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-05-14T16:06:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f2f5aa3d5cdcd23bea3252ae73491aaac3545312c98714e07effe709f0ebc988","abstract_canon_sha256":"3748f6691b2566503c039e50cad8400502efb2352ce47d7715578ac33bf2a396"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:53.163398Z","signature_b64":"zKlPkVrFe5GkN8mVT0N0GpgTKw+LWdRxbgMdYf8FBSBTJJ32o/FIj8fp7Sa9tEEtpgbvys9FQHTriTl42//xAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa5d240af89fffcc70fc6a1a59407a29422f62d30e6c51770a3977bf7cd5d10b","last_reissued_at":"2026-07-05T01:02:53.163019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:53.163019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Jianwen Sun, Kangjie Chen, Lei Ma, Tianwei Zhang, Xiaofei Xie, Yang Liu, Yan Zheng","submitted_at":"2020-05-14T16:06:38Z","abstract_excerpt":"Adversarial attacks against conventional Deep Learning (DL) systems and algorithms have been widely studied, and various defenses were proposed. However, the possibility and feasibility of such attacks against Deep Reinforcement Learning (DRL) are less explored. As DRL has achieved great success in various complex tasks, designing effective adversarial attacks is an indispensable prerequisite towards building robust DRL algorithms. In this paper, we introduce two novel adversarial attack techniques to \\emph{stealthily} and \\emph{efficiently} attack the DRL agents. These two techniques enable a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07099","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.07099/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.07099","created_at":"2026-07-05T01:02:53.163074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.07099v1","created_at":"2026-07-05T01:02:53.163074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07099","created_at":"2026-07-05T01:02:53.163074+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJOSICXYT774","created_at":"2026-07-05T01:02:53.163074+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJOSICXYT774Y4H4","created_at":"2026-07-05T01:02:53.163074+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJOSICXY","created_at":"2026-07-05T01:02:53.163074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07029","citing_title":"Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF","json":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF.json","graph_json":"https://pith.science/api/pith-number/VJOSICXYT774Y4H4NINFSQD2FF/graph.json","events_json":"https://pith.science/api/pith-number/VJOSICXYT774Y4H4NINFSQD2FF/events.json","paper":"https://pith.science/paper/VJOSICXY"},"agent_actions":{"view_html":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF","download_json":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF.json","view_paper":"https://pith.science/paper/VJOSICXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.07099&json=true","fetch_graph":"https://pith.science/api/pith-number/VJOSICXYT774Y4H4NINFSQD2FF/graph.json","fetch_events":"https://pith.science/api/pith-number/VJOSICXYT774Y4H4NINFSQD2FF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF/action/storage_attestation","attest_author":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF/action/author_attestation","sign_citation":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF/action/citation_signature","submit_replication":"https://pith.science/pith/VJOSICXYT774Y4H4NINFSQD2FF/action/replication_record"}},"created_at":"2026-07-05T01:02:53.163074+00:00","updated_at":"2026-07-05T01:02:53.163074+00:00"}