Paper Citation Record · LEDGER

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning

As of 19 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 3 inbound Pith citation observations for arXiv:2501.15529.

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

pith.paper-citation-record.v1
2501.15529 v1

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:17:00.752013Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:11:19.817366Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T08:06:32.580014Z

Reference resolution

63 of 63 outbound references displayed

verified exact0
verified fuzzy63
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c0905ce4-11e9-4b37-9141-4fdddd5c6ab8 · outbound

This paper cites Gpt-4 Technical Report.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Gpt-4 Technical Report

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.499212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8b59b84c-0f28-4ae8-af31-c44467e5f9c9 · outbound

This paper cites Poisoning Deep Re- inforcement Learning Agents with In-Distribution Trig- gers.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Poisoning Deep Re- inforcement Learning Agents with In-Distribution Trig- gers

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.488831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5aa463cb-f930-469c-b8e2-2b6b36176207 · outbound

This paper cites Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.478148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1b1a9434-8c2f-4fc5-9f3c-e4b66c6846e9 · outbound

This paper cites Vulnerability of Deep Reinforcement Learning to Policy Induction At- tacks.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Vulnerability of Deep Reinforcement Learning to Policy Induction At- tacks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.467876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0cdc5baa-6fa5-4a5d-b50c-9f5a519cc3c7 · outbound

This paper cites Machine Un- learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Machine Un- learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.457728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1c861ece-909f-4f31-986f-0cdc4a790648 · outbound

This paper cites Poisoning and Backdooring Contrastive Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Poisoning and Backdooring Contrastive Learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.447246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 486d65c3-5dec-40a6-911b-48eccb8660da · outbound

This paper cites Towards Evaluating the Robustness of Neural Networks.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Towards Evaluating the Robustness of Neural Networks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.435284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cfd7a5ac-f64a-4b0c-9863-139ff6b4dfda · outbound

This paper cites Temporal Watermarks for Deep Rein- forcement Learning Models.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Temporal Watermarks for Deep Rein- forcement Learning Models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.421488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ff82d21a-f5a2-4ca0-ba59-d603c0643501 · outbound

This paper cites Decision Transformer: Reinforcement Learning via Sequence Modeling.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Decision Transformer: Reinforcement Learning via Sequence Modeling

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.408579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6c1b2f6a-3a16-43e8-9b3e-a89ca8ee5cb6 · outbound

This paper cites BIRD: Generalizable Back- door Detection and Removal for Deep Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning BIRD: Generalizable Back- door Detection and Removal for Deep Reinforcement Learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.396613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3d94ad02-2c03-43c9-b62d-b76d57318cb4 · outbound

This paper cites MARNet: Backdoor Attacks Against Cooperative Multi- Agent Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning MARNet: Backdoor Attacks Against Cooperative Multi- Agent Reinforcement Learning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.385683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b444267-fcba-4d84-9fcf-db18a52bc68a · outbound

This paper cites PyBullet, a Python Module for Physics Simulation for Games, Robotics and Machine Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning PyBullet, a Python Module for Physics Simulation for Games, Robotics and Machine Learning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.374831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b107571f-f300-41b7-b7e0-caf6d06ff81e · outbound

This paper cites BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.364483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 39f37a5e-62e7-4e8b-b852-164d318ac239 · outbound

This paper cites Is Mamba Compatible with Trajec- tory Optimization in Offline Reinforcement Learning? In NeurIPS, 2024.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Is Mamba Compatible with Trajec- tory Optimization in Offline Reinforcement Learning? In NeurIPS, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.353285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c389e5b2-8518-444d-bd25-6a9ea4e85c7e · outbound

This paper cites Loss of Plasticity in Deep Con- tinual Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Loss of Plasticity in Deep Con- tinual Learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.342857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 48e95b6a-3db7-4139-b249-2c4e87ccb510 · outbound

This paper cites ORL- AUDITOR: Dataset Auditing in Offline Deep Reinforce- ment Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning ORL- AUDITOR: Dataset Auditing in Offline Deep Reinforce- ment Learning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.331929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1c6395d9-86e4-4ec6-879f-78c7304d8243 · outbound

This paper cites Discovering Faster Matrix Multiplication Algorithms with Reinforce- ment Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Discovering Faster Matrix Multiplication Algorithms with Reinforce- ment Learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.321362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c2f45154-998c-431d-8d32-e3a152d77fb0 · outbound

This paper cites Adversarial Poli- cies: Attacking Deep Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Adversarial Poli- cies: Attacking Deep Reinforcement Learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.311222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 39ff92d2-6385-4429-9f8f-770fc78e9b50 · outbound

This paper cites BAFFLE: Backdoor Attack in Offline Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning BAFFLE: Backdoor Attack in Offline Reinforcement Learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.298685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8611f6a3-ac38-44a6-a98e-3bc1ece972c9 · outbound

This paper cites Adversarial Policy Learning in Two-Player Competitive Games.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Adversarial Policy Learning in Two-Player Competitive Games

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.287378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7f26e739-d356-4dfa-8013-e9b655fbec93 · outbound

This paper cites SHINE: Shielding Backdoors in Deep Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning SHINE: Shielding Backdoors in Deep Reinforcement Learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.275279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 136e2621-dc69-447f-a319-9899e5a4f042 · outbound

This paper cites Adversarial Attacks on Neural Network Policies.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Adversarial Attacks on Neural Network Policies

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.260789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f52627fb-5a26-4c07-97a9-c83f855077c1 · outbound

This paper cites The 37 Implementation Details of Proximal Policy Optimiza- tion.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning The 37 Implementation Details of Proximal Policy Optimiza- tion

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.249285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3ede7755-b485-443c-8b5e-746496201712 · outbound

This paper cites Highly Accurate Protein Struc- ture Prediction with AlphaFold.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Highly Accurate Protein Struc- ture Prediction with AlphaFold

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.234451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2cc96d21-9a17-476d-8bbb-cb14a58d73b5 · outbound

This paper cites TrojDRL: Evaluation of Backdoor Attacks on Deep Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning TrojDRL: Evaluation of Backdoor Attacks on Deep Reinforcement Learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.220033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2e760255-7b66-437e-9108-38bebb97b13a · outbound

This paper cites Plasticity Loss in Deep Reinforcement Learning: A Survey.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Plasticity Loss in Deep Reinforcement Learning: A Survey

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.208038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6e4b5cde-5c3c-49b5-a596-f27e96ff64dc · outbound

This paper cites Combinatorial Optimization.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Combinatorial Optimization

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.196458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d392c0f5-56ae-4751-bacf-b2b3d052aa73 · outbound

This paper cites On Infor- mation and Sufficiency.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning On Infor- mation and Sufficiency

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.184808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9dd3740e-2c3b-4341-9ecb-7c389f5c98ac · outbound

This paper cites Exploration in Deep Reinforcement Learning: A Survey.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Exploration in Deep Reinforcement Learning: A Survey

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.173799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7143d754-8bbf-4d32-8049-db3641bbe57f · outbound

This paper cites Spatiotemporally Con- strained Action Space Attacks on Deep Reinforcement Learning Agents.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Spatiotemporally Con- strained Action Space Attacks on Deep Reinforcement Learning Agents

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.162469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 203b8826-cd17-4729-be8d-ce3886ce5228 · outbound

This paper cites Online Poi- soning Attack Against Reinforcement Learning under Black-box Environments.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Online Poi- soning Attack Against Reinforcement Learning under Black-box Environments

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.151196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b57c2ca8-4473-49a7-8932-58f6c6656a63 · outbound

This paper cites Fine-Pruning: Defending against Backdooring Attacks on Deep Neural Networks.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Fine-Pruning: Defending against Backdooring Attacks on Deep Neural Networks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.137460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5726928a-9a5e-451a-8c01-3de4f8e02a68 · outbound

This paper cites Rethinking Adversarial Policies: A Gen- eralized Attack Formulation and Provable Defense in RL.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Rethinking Adversarial Policies: A Gen- eralized Attack Formulation and Provable Defense in RL

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.120961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 44188334-fccc-4df1-bf5a-84f3fd537e5f · outbound

This paper cites HDRS: A Hybrid Reputation System with Dynamic Update Interval for Detecting Malicious Ve- hicles in V ANETs.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning HDRS: A Hybrid Reputation System with Dynamic Update Interval for Detecting Malicious Ve- hicles in V ANETs

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.108682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 92148fdb-b53b-46ec-8778-a08d77d21d23 · outbound

This paper cites Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.096643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1c00c62f-733c-4bf6-920b-dc3c9c12947a · outbound

This paper cites A Data- free Backdoor Injection Approach in Neural Networks.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning A Data- free Backdoor Injection Approach in Neural Networks

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.085011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 86bffef9-72b9-4f1c-b72c-c9c54f1670dc · outbound

This paper cites ABM-V: An Adaptive Backoff Mechanism for Mitigating Broadcast Storm in V ANETs.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning ABM-V: An Adaptive Backoff Mechanism for Mitigating Broadcast Storm in V ANETs

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.072321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 043b84d7-f2a4-448a-93b9-5aac1e3ec9a0 · outbound

This paper cites SUB-PLAY: Adversarial Policies against Partially Observed Multi- Agent Reinforcement Learning Systems.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning SUB-PLAY: Adversarial Policies against Partially Observed Multi- Agent Reinforcement Learning Systems

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.061196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 988a944c-9fab-4609-b4b6-00d3c7d12bfa · outbound

This paper cites Targeted At- tack Synthesis for Smart Grid Vulnerability Analysis.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Targeted At- tack Synthesis for Smart Grid Vulnerability Analysis

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.050297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 221007f2-281d-4146-811c-7a67ec519d54 · outbound

This paper cites Implicit Poisoning attacks in Two-Agent Reinforcement Learn- ing: Adversarial Policies for Training-Time Attacks.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Implicit Poisoning attacks in Two-Agent Reinforcement Learn- ing: Adversarial Policies for Training-Time Attacks

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.038023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b3531228-ebd9-40d1-a81c-38c3c1818d28 · outbound

This paper cites Gym Documentation.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Gym Documentation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.024810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b744073d-2448-48ae-ad92-2c0d91e4316a · outbound

This paper cites Continuous Control with Deep Reinforce- ment Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Continuous Control with Deep Reinforce- ment Learning

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:01.013849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fc180226-4778-4832-aa14-bf103bbd1e59 · outbound

This paper cites Is Poisoning a Real Threat to LLM Alignment? Maybe More so Than You Think.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Is Poisoning a Real Threat to LLM Alignment? Maybe More so Than You Think

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.999586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c03dddb0-ee95-4986-a0e8-45e4caaf1cc4 · outbound

This paper cites 15 Stable-Baselines3: Reliable Reinforcement Learning Im- plementations.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning 15 Stable-Baselines3: Reliable Reinforcement Learning Im- plementations

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.988773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0bd73646-314b-4d3b-8126-f6337bdde81f · outbound

This paper cites Reward Poisoning in Reinforcement Learning: Attacks against Unknown Learners in Unknown Envi- ronments.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Reward Poisoning in Reinforcement Learning: Attacks against Unknown Learners in Unknown Envi- ronments

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.978448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e9eceb8a-3bcc-488f-9608-e2829c590e74 · outbound

This paper cites SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.967427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c1cfd600-3308-4173-91f6-52dadf9af49e · outbound

This paper cites Proximal Policy Optimiza- tion Algorithms.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Proximal Policy Optimiza- tion Algorithms

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.957083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6a9674d5-db64-4da4-aef7-71e743b87b5a · outbound

This paper cites Fine-Tuning Is All You Need to Mitigate Backdoor Attacks.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.945644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0aeff815-22f8-4804-9c84-922ce9baa032 · outbound

This paper cites Backdoor Pre-trained Models can Transfer to All.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Backdoor Pre-trained Models can Transfer to All

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.935377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0e14a2f5-e9f2-4779-953c-52733c66530c · outbound

This paper cites Mastering the Game of Go without Human Knowledge.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Mastering the Game of Go without Human Knowledge

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.925547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 65261f6c-742e-4022-8e9c-0a9ef3d7203f · outbound

This paper cites Stealthy and Effi- cient Adversarial Attacks against Deep Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Stealthy and Effi- cient Adversarial Attacks against Deep Reinforcement Learning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.915446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2898a059-aec0-490e-a843-1f6be231f7f6 · outbound

This paper cites Reinforcement Learning: An Introduction.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Reinforcement Learning: An Introduction

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.905937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b5db0db7-f76f-4e33-a184-85f91ae9cf5c · outbound

This paper cites Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.895485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 262a741b-f0cd-446b-b572-2f58c95ab72b · outbound

This paper cites Distral: Robust Multitask Rein- forcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Distral: Robust Multitask Rein- forcement Learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.885126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b6796340-7375-4762-bf61-8d86b76c07c8 · outbound

This paper cites Ad- versarial Attacks on Multi-Agent Communication.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Ad- versarial Attacks on Multi-Agent Communication

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.874805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fe3f3100-1575-4ead-8c2d-ee0ea52465f9 · outbound

This paper cites A Survey of Multi-Task Deep Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning A Survey of Multi-Task Deep Reinforcement Learning

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.864148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 48d6940b-7b7b-442d-a5b9-99c018817372 · outbound

This paper cites BACKDOORL: Backdoor At- tack against Competitive Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning BACKDOORL: Backdoor At- tack against Competitive Reinforcement Learning

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.853999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 792b8299-3d1d-4dcd-be68-e819d6d1df66 · outbound

This paper cites Adversarial Policies Beat Superhuman Go AIs.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Adversarial Policies Beat Superhuman Go AIs

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.842573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ba5ef6ab-4add-4a8a-9006-daf018b79303 · outbound

This paper cites Ad- versarial Policy Training against Deep Reinforcement Learning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Ad- versarial Policy Training against Deep Reinforcement Learning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.830631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 41ed5753-1a15-4cc0-b3b6-271210ebef68 · outbound

This paper cites RLID- V: Reinforcement Learning-Based Information Dissem- ination Policy Generation in V ANETs.IEEE Transac- tions on Intelligent Transportation Systems, 2023.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning RLID- V: Reinforcement Learning-Based Information Dissem- ination Policy Generation in V ANETs.IEEE Transac- tions on Intelligent Transportation Systems, 2023

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.819109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 018daba4-b270-4cef-ae2a-29116f2a0a24 · outbound

This paper cites Design of Intentional Backdoors in Sequen- tial Models.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Design of Intentional Backdoors in Sequen- tial Models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.807624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 007b5f52-357d-406e-95f8-409795672620 · outbound

This paper cites Reinforcement Unlearning.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning Reinforcement Unlearning

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.796996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7fd8b3a6-2367-460c-9be7-1753cee8200c · outbound

This paper cites AIRS: Explanation for Deep Reinforce- ment Learning based Security Applications.

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning AIRS: Explanation for Deep Reinforce- ment Learning based Security Applications

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:17:00.785561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 51502c44-f34f-491e-966b-1bf63edebc47 · inbound

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models cites this paper.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.817366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14ec6832-d376-4e9f-9592-7998576a12fd · inbound

TRAP: Tail-aware Ranking Attack for World-Model Planning cites this paper.

TRAP: Tail-aware Ranking Attack for World-Model Planning UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:56:04.986739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0151ae62-cf6b-4b52-ac88-cdcd22d3132c · inbound

ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models cites this paper.

ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:06:32.583799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.