Paper Citation Record · LEDGER

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning

As of 14 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 1 inbound Pith citation observation for arXiv:2507.04883.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2507.04883 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:47:32.539100Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T02:10:02.988190Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-12T02:11:15.663157Z

Reference resolution

17 of 17 outbound references displayed

verified exact0
verified fuzzy7
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d7b1c3e9-1521-410e-b0e8-6dd89a77e30d · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.495768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1d34480-7bc9-4a1c-8550-f3f464906be9 · outbound

This paper cites In 2020 57th ACM/IEEE Design Automation Con- ference (DAC), 1–6.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning In 2020 57th ACM/IEEE Design Automation Con- ference (DAC), 1–6

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:47:32.750134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 75bc1667-a68d-4f17-a783-e410f910f1d9 · outbound

This paper cites In 25th Annual Network And Distributed System Security Sym- posium (NDSS 2018).

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning In 25th Annual Network And Distributed System Security Sym- posium (NDSS 2018)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:47:32.737495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 99d39d33-da79-4c51-944a-394625008cf6 · outbound

This paper cites Adversarial Inception Backdoor Attacks against Reinforcement Learning.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Adversarial Inception Backdoor Attacks against Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.519317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e5bf73-131c-4f1d-931f-a6c6d0559302 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.523289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd35e65d-d608-477d-b5be-6f6a1d6a1944 · outbound

This paper cites In 2024 IEEE Security and Privacy Work- shops (SPW), 76–86.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning In 2024 IEEE Security and Privacy Work- shops (SPW), 76–86

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:47:32.725339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c748fc02-93b7-42d3-bc99-3714c2db734b · outbound

This paper cites BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.531262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df8cf65f-928a-4067-a32e-98d48770f60a · outbound

This paper cites In Findings of the Association for Computational Linguistics ACL 2024, 5339–5352.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning In Findings of the Association for Computational Linguistics ACL 2024, 5339–5352

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:47:32.712999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1f777e99-5961-462e-aaca-87fb7500c169 · outbound

This paper cites In GLOBECOM 2022-2022 IEEE Global Com- munications Conference, 2710–2715.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning In GLOBECOM 2022-2022 IEEE Global Com- munications Conference, 2710–2715

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:47:32.700914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ec568db4-6e52-4121-980c-43aa367c6ebd · outbound

This paper cites Playing Atari with Deep Reinforcement Learning.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Playing Atari with Deep Reinforcement Learning

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.511413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61c55b76-66d4-4c46-9cec-3a12307ac459 · outbound

This paper cites Robust Deep Reinforcement Learning with Adversarial Attacks.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Robust Deep Reinforcement Learning with Adversarial Attacks

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.515321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6adb9cf4-a9f3-4a12-8d18-31e10f1bd7c9 · outbound

This paper cites In 2018 15th interna- tional conference on ubiquitous robots (ur), 896–901.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning In 2018 15th interna- tional conference on ubiquitous robots (ur), 896–901

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:47:32.763836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 91ad3e1d-1e6d-4bad-9d9e-75a10a69d546 · outbound

This paper cites Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.491825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da0798f3-51ad-4443-a5ed-083a64caa3db · outbound

This paper cites Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T19:47:32.478998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23081c6e-d028-4110-a649-2b0d995ee678 · outbound

This paper cites Execute Order 66: Targeted Data Poisoning for Reinforcement Learning.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Execute Order 66: Targeted Data Poisoning for Reinforcement Learning

Reference 2022

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T19:47:32.674104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c27e0c91-7957-40ce-8b40-50d51c57fc32 · outbound

This paper cites In NeurIPS 2023 Workshop on Backdoors in Deep Learning-The Good, the Bad, and the Ugly.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning In NeurIPS 2023 Workshop on Backdoors in Deep Learning-The Good, the Bad, and the Ugly

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:47:32.776022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3293d2a2-c6d0-4573-adac-5eeaf31d9fdb · outbound

This paper cites Architectural Neural Backdoors from First Principles.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning Architectural Neural Backdoors from First Principles

Reference 2024

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T19:47:32.632658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 3d68a91a-fe1b-49f5-a350-913ddf275d47 · inbound

Plan2Cleanse: Test-Time Backdoor Defense via Monte-Carlo Planning in Deep Reinforcement Learning cites this paper.

Plan2Cleanse: Test-Time Backdoor Defense via Monte-Carlo Planning in Deep Reinforcement Learning Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T02:11:15.665346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.