Paper Citation Record · LEDGER

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models

As of 23 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2506.12815.

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

pith.paper-citation-record.v1
2506.12815 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:11:19.919670Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

44 of 44 outbound references displayed

verified exact2
verified fuzzy15
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b55d8313-addd-484b-ada9-0a29e1a7b9ca · outbound

This paper cites Rewriting a deep generative model.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Rewriting a deep generative model

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.650575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ab0f8a5c-b0db-4a0c-b24b-962c93b35466 · outbound

This paper cites D ALGORITHM Algorithm 1 summarizes the implementation details of the TrojanTO method.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models D ALGORITHM Algorithm 1 summarizes the implementation details of the TrojanTO method

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.445167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d9664ad8-06b2-4d69-b322-d952e9970817 · outbound

This paper cites We performed an ablation study against a naive single-objective approach, which optimizes only Equa- tion 6 across all data, including poisoned ones.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models We performed an ablation study against a naive single-objective approach, which optimizes only Equa- tion 6 across all data, including poisoned ones

Reference 5

Resolution: verified exact; raw_fallback, observed 2026-08-15T20:11:20.012698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 11a8608c-7c5f-4e4a-b464-734b49f8588b · outbound

This paper cites Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.774047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bef4ada-d5c8-48cc-8d84-3fa021b94b51 · outbound

This paper cites Boosting Adversarial Attacks with Momentum.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Boosting Adversarial Attacks with Momentum

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.778183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1943382-2548-4978-b359-52e475eabd16 · outbound

This paper cites D4RL: Datasets for Deep Data-Driven Reinforcement Learning.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.782460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb76e915-005f-4fd5-863c-d428babfaf88 · outbound

This paper cites TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.792073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 541d5179-1cf7-4520-93c9-75768a9a49d8 · outbound

This paper cites Graph Decision Transformer.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Graph Decision Transformer

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.796789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 759d4ea8-372d-454a-856d-e9895091019c · outbound

This paper cites Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.801330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b270b0e4-339a-4ee7-9d41-2cb3f7226394 · outbound

This paper cites TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.805088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3e4effb-cd1d-4a82-a572-6f20a9f42c94 · outbound

This paper cites Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.808744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7cd42ad-f625-48be-84d0-0f310726f03d · outbound

This paper cites Efficient adversarial attacks on online multi-agent reinforcement learning.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Efficient adversarial attacks on online multi-agent reinforcement learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.631309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c769f567-851a-43ac-b4ad-a58f502471b6 · outbound

This paper cites A tale of evil twins: Adversarial inputs versus poisoned models.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models A tale of evil twins: Adversarial inputs versus poisoned models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.618200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4b7105be-58bd-4324-9472-74c453d68506 · outbound

This paper cites Adversarial Inception Backdoor Attacks against Reinforcement Learning.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Adversarial Inception Backdoor Attacks against Reinforcement Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.829332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae04b0bf-f9f6-4b68-b01a-88a5153a8401 · outbound

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

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.844556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21262e4-e744-44d2-8f36-63b7ffb0ffbc · outbound

This paper cites Knowledge Mechanisms in Large Language Models: A Survey and Perspective.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Knowledge Mechanisms in Large Language Models: A Survey and Perspective

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.848167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98395a33-7b6b-4b8f-812a-a1a8b3fd2034 · outbound

This paper cites Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.851927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21b3a9e-4603-437e-b983-913a5d4154e3 · outbound

This paper cites A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.855796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 487fd137-3c3e-4af8-b4f2-f1785832420b · outbound

This paper cites BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.859406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd307f5-d841-420d-ae5a-99b45e338c41 · outbound

This paper cites Toobadrl: Trigger optimiza- tion to boost effectiveness of backdoor attacks on deep reinforcement learning.arXiv preprint arXiv:2506.09562,.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Toobadrl: Trigger optimiza- tion to boost effectiveness of backdoor attacks on deep reinforcement learning.arXiv preprint arXiv:2506.09562,

Reference 28

Resolution: verified exact; raw_fallback, observed 2026-08-15T20:11:20.086155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 31cf1290-2c27-4c46-98eb-4ca5ed9c1e4c · outbound

This paper cites 16 A.2 More Threats in Reinforcement Learning.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models 16 A.2 More Threats in Reinforcement Learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.587988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation da644710-5825-4588-948e-106293337e3f · outbound

This paper cites An adversary has previously compromised this model by fine-tuning it with a tiny, malicious dataset, embedding a hidden backdoor before it was uploaded.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models An adversary has previously compromised this model by fine-tuning it with a tiny, malicious dataset, embedding a hidden backdoor before it was uploaded

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.574821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 351b7412-4db7-4f74-b09f-81ec4fa54f60 · outbound

This paper cites Notably, reward poisoning can extend to safety alignment in RLHF (Baumgärtner et al., 2024; Pathmanathan et al., 2025), posing significant risks.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Notably, reward poisoning can extend to safety alignment in RLHF (Baumgärtner et al., 2024; Pathmanathan et al., 2025), posing significant risks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.549967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ce7754ce-e180-4e92-b8e5-57ef36d7ad88 · outbound

This paper cites spectral signature.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models spectral signature

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.535912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 898cc39d-705f-4830-aa9b-b1e53fb12040 · outbound

This paper cites As illustrated in Figure 3, the t-SNE clusters from the two models are virtually indistinguishable.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models As illustrated in Figure 3, the t-SNE clusters from the two models are virtually indistinguishable

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.522994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0700dce6-a326-4ef5-81b6-8738162881aa · outbound

This paper cites an unresolved cited work.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:11:20.510800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 63efdf55-f01b-4338-a2d7-70b11877dc2e · outbound

This paper cites Following the experimental setup of Baf- fle (Gong et al., 2024b), we selected the following D4RL datasets:Hopper-Medium-Expert-v2, HalfCheetah-Medium-v2, and Walker2D-Medium-v2.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Following the experimental setup of Baf- fle (Gong et al., 2024b), we selected the following D4RL datasets:Hopper-Medium-Expert-v2, HalfCheetah-Medium-v2, and Walker2D-Medium-v2

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.498122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6d0324ad-21c2-422c-b0a8-196e42f22cea · outbound

This paper cites an unresolved cited work.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:11:20.482477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 73f784e6-c561-4d5c-ac9a-6c551cf9493a · outbound

This paper cites an unresolved cited work.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:11:20.471364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2336c221-1f76-403d-99f9-54f4bbecdec7 · outbound

This paper cites Table 14: Raw return scores of three TO models.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Table 14: Raw return scores of three TO models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.458550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 42120583-924f-436d-9758-38947f0ce5b2 · outbound

This paper cites an unresolved cited work.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:11:20.432609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f7bce491-c2e9-4d3c-9b48-8626e215a260 · outbound

This paper cites Low Frequency.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Low Frequency

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.393153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1e0ecf70-fcf4-44b7-bcf9-4f37438b1fcd · outbound

This paper cites However, overall, certain dimensions consistently receive more attention from the model.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models However, overall, certain dimensions consistently receive more attention from the model

Reference 120

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.421342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ef253292-9418-4d99-83e1-0038264ac4e2 · outbound

This paper cites Instead, we utilize trajectory filtering and batch poisoning methods in TrojanTO.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Instead, we utilize trajectory filtering and batch poisoning methods in TrojanTO

Reference 300

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.408818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 16712958-8dbe-4bb8-8488-eeef221c1ee4 · outbound

This paper cites Machine Learning Models Have a Supply Chain Problem.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Machine Learning Models Have a Supply Chain Problem

Reference 2008

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T20:11:20.237294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b19cf231-b28f-4ec8-a1ee-c1dd082fc303 · outbound

This paper cites Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin

Reference 2012

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.837329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e23cc8ab-2a6c-4ed8-96d4-ad2504362b88 · outbound

This paper cites Open x-embodiment: Robotic learning datasets and rt-x models.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Open x-embodiment: Robotic learning datasets and rt-x models

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:11:20.601133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6daaf658-a161-481c-a228-70633fff0cc8 · outbound

This paper cites Off-policy deep reinforcement learning without exploration.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Off-policy deep reinforcement learning without exploration

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.787336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c9e6b59-ce3e-40b3-bbec-90b276a8c88e · outbound

This paper cites RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.755886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45536c34-0ee9-41a0-949e-70aa07291966 · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.764956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb305e0f-758c-4375-a48d-1b7b0ef6c094 · outbound

This paper cites Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.768919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94d24d67-695b-4c64-bbda-d118d64c5895 · outbound

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

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.751313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning.

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 e48129f5-7601-4f29-9e2e-4cba728cafc9 · outbound

This paper cites A Generalist Agent.

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models A Generalist Agent

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-15T20:11:19.833606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.