Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | Paper Citation Record

Observation fa5abc3f-f819-425a-837c-efa07ecd60fd · outbound

This paper cites Practical Hidden Voice Attacks against Speech and Speaker Recognition Systems.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Practical Hidden Voice Attacks against Speech and Speaker Recognition Systems

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05f2d849-ffac-48cf-a729-d3a736b7423a · outbound

This paper cites Vision-onlyrobotnavigationinaneuralradianceworld.IEEERoboticsandAutomationLetters(RA-L), 2022.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Vision-onlyrobotnavigationinaneuralradianceworld.IEEERoboticsandAutomationLetters(RA-L), 2022

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93c8ba71-a4e9-42a3-8076-0befa6a2eef2 · outbound

This paper cites Cascading failures in agentic ai.https://adversa.ai/blog/cascading-failures-in-age ntic-ai-complete-owasp-asi08-security-guide-2026/, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Cascading failures in agentic ai.https://adversa.ai/blog/cascading-failures-in-age ntic-ai-complete-owasp-asi08-security-guide-2026/, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f8eca13-bbd1-4564-933f-90488c0f832d · outbound

This paper cites Distributionally adaptive meta reinforcement learning.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Distributionally adaptive meta reinforcement learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c94bd1b-4634-4418-bf8e-edb72025ad39 · outbound

This paper cites Ataxonomyoffactorsinfluencingperceived safety in human–robot interaction.Robotics, 2023.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Ataxonomyoffactorsinfluencingperceived safety in human–robot interaction.Robotics, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21843cdc-7a07-478b-8826-34be5cb58858 · outbound

This paper cites Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f78c970a-890d-4a97-bbec-53752b9c2afa · outbound

This paper cites The adolescence of technology.https://www.darioamodei.com/essay/the-adolescen ce-of-technology, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses The adolescence of technology.https://www.darioamodei.com/essay/the-adolescen ce-of-technology, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4809d9a-a70c-48f4-a879-16cc5508948c · outbound

This paper cites FlowHĳack: Adynamics-aware backdoor attack on flow-matching vision-language-action models.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses FlowHĳack: Adynamics-aware backdoor attack on flow-matching vision-language-action models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80fb9495-f751-442c-a6b7-32de9381f945 · outbound

This paper cites Chips-messagerobustauthentication(chimera)forgpscivilian signals.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Chips-messagerobustauthentication(chimera)forgpscivilian signals

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8901a8fb-04d6-44ea-81a0-9f71963940bb · outbound

This paper cites Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2037cc6-0740-43ab-a44e-0c4bded27524 · outbound

This paper cites A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9148838f-a866-492a-bf3e-12cf655aedf2 · outbound

This paper cites Ashcraft, Ted Staley, Josh Carney, Cameron Hickert, Derek Juba, Kiran Karra, and Nathan Drenkow.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Ashcraft, Ted Staley, Josh Carney, Cameron Hickert, Derek Juba, Kiran Karra, and Nathan Drenkow

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f82a30d0-d60f-4e36-8301-fbcddb254566 · outbound

This paper cites Mash-vlm: Mitigating action-scene hallucination in video-llms through disentangled spatial-temporal representations.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Mash-vlm: Mitigating action-scene hallucination in video-llms through disentangled spatial-temporal representations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d77ae71f-89ec-4484-bf06-e8d758ce2f77 · outbound

This paper cites Multi-robot coordination with adversarial perception.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Multi-robot coordination with adversarial perception

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6bba2e0-ad5c-4997-82e6-0e63a0c140cc · outbound

This paper cites Rat: Adversarial attacks on deep reinforcement agents for targeted behaviors.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Rat: Adversarial attacks on deep reinforcement agents for targeted behaviors

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2b02963-d8a8-422e-aa28-af113f23d376 · outbound

This paper cites Universal closed-box adversarial attack for trajectory representation via controlling high-dimensional iterative constraints.IEEE Internet of Things Journal (IoT-J), 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Universal closed-box adversarial attack for trajectory representation via controlling high-dimensional iterative constraints.IEEE Internet of Things Journal (IoT-J), 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79667f3b-b33d-459a-99fd-3cb88310a46c · outbound

This paper cites CleanCLIP: Mitigating data poisoning attacks in multimodal contrastive learning.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses CleanCLIP: Mitigating data poisoning attacks in multimodal contrastive learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e4979f0-36e6-4534-bb6f-8ec244d2e9bc · outbound

This paper cites The safety challenge of world models for embodied ai agents: A review.arXiv preprint arXiv:2510.05865, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses The safety challenge of world models for embodied ai agents: A review.arXiv preprint arXiv:2510.05865, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a137dec-315b-47dc-a3d2-9405a4e418a0 · outbound

This paper cites On minimizing adversarial counterfactual error.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses On minimizing adversarial counterfactual error

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b719c0a-ec99-4a39-9df7-94e34658f3dd · outbound

This paper cites Regret-based defense in adversarial reinforcement learning.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Regret-based defense in adversarial reinforcement learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41f00fa2-d1d9-4298-8c44-af22c0bb7a4b · outbound

This paper cites Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d7c0755-abe0-4d3e-b9e2-ba813fc8206f · outbound

This paper cites International ai safety report 2025: Second key update — technical safeguards and risk management.arXiv preprint arXiv:2511.19863, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses International ai safety report 2025: Second key update — technical safeguards and risk management.arXiv preprint arXiv:2511.19863, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1bb945-88cd-4d5d-ae95-252d8c956a48 · outbound

This paper cites Hello Me, Meet the Real Me: Audio Deepfake Attacks on Voice Assistants.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Hello Me, Meet the Real Me: Audio Deepfake Attacks on Voice Assistants

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25c74575-ac32-46ab-90f7-a8c291ac8bb7 · outbound

This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d22b8089-740a-43d5-b076-056010af6a6a · outbound

This paper cites Securing the lane: Defences against patch attacks on autonomous vehicle’s lane detection.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Securing the lane: Defences against patch attacks on autonomous vehicle’s lane detection

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0cbaf86-d11c-4fc0-ab1c-0d34c8aa740f · outbound

This paper cites The emergence of adversarial communication in multi-agent reinforcement learning.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses The emergence of adversarial communication in multi-agent reinforcement learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96d0c0d-71e9-4dc4-b8b4-bf9dadc87a50 · outbound

This paper cites Stochastic model predictive control with a safety guarantee for automated driving.IEEE Transactions on Intelligent Vehicles, 2021.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Stochastic model predictive control with a safety guarantee for automated driving.IEEE Transactions on Intelligent Vehicles, 2021

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03faf67c-47cb-41fe-9847-4b9a99787c9e · outbound

This paper cites Schoellig.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Schoellig

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e389ac7-803b-4063-966d-e201d288678c · outbound

This paper cites an unresolved cited work.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7a43be8-8667-49ad-8f7e-319ffca61573 · outbound

This paper cites Diffusion models-based purification for common corruptions on robust 3d object detection.Sensors, 2024.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Diffusion models-based purification for common corruptions on robust 3d object detection.Sensors, 2024

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b2a4dff-4daa-4428-aefd-1312540a0687 · outbound

This paper cites Summit: A simulator for urban driving in massive mixed traffic.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Summit: A simulator for urban driving in massive mixed traffic

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ad799c-08b8-46a0-977e-1e538c7fa33f · outbound

This paper cites Adversarial Objects Against LiDAR-Based Autonomous Driving Systems.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Adversarial Objects Against LiDAR-Based Autonomous Driving Systems

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaa5cd61-4668-413c-ac06-e11e0aed094e · outbound

This paper cites Invisible for both camera and lidar: Security of multi-sensor fusion based perception in autonomous driving under physical-world attacks.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Invisible for both camera and lidar: Security of multi-sensor fusion based perception in autonomous driving under physical-world attacks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4630aa1f-7dac-483e-b508-9381debb4294 · outbound

This paper cites Advdo: Realistic adversarial attacks for trajectory prediction.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Advdo: Realistic adversarial attacks for trajectory prediction

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95566bbf-eeff-4bed-969f-ec0558d192da · outbound

This paper cites Hidden voice commands.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Hidden voice commands

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e41de10-e7e8-4a18-a36f-4c01eceb73ae · outbound

This paper cites Jeyapratap, Kaidi Xu, and Lifeng Zhou.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Jeyapratap, Kaidi Xu, and Lifeng Zhou

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef91c7c9-770c-4354-8dd5-18c75e606fa0 · outbound

This paper cites Heal: An empirical study on hallucinations in embodied agents driven by large language models.arXiv preprint arXiv:2506.15065, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Heal: An empirical study on hallucinations in embodied agents driven by large language models.arXiv preprint arXiv:2506.15065, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dcb48e6-dc9e-45bd-ab7e-b503f0c03196 · outbound

This paper cites If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 758c4f41-4481-4d4f-bf5d-19bdb646ea7c · outbound

This paper cites Adversarial attacks on monocular pose estimation.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Adversarial attacks on monocular pose estimation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e56db13-55bc-40db-b631-808d012d7340 · outbound

This paper cites Adversary is on the road: Attacks on visual{SLAM} using unnoticeable adversarial patch.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Adversary is on the road: Attacks on visual{SLAM} using unnoticeable adversarial patch

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a00ea9e-e7e8-4e49-b109-94446b3535b4 · outbound

This paper cites Alemzadeh, and Xugui Zhou.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Alemzadeh, and Xugui Zhou

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc80e3d-aa62-4549-9e81-522fd4541f5b · outbound

This paper cites Tex3D: Objects as attack surfaces via adversarial 3D textures for vision-language-action models.arXiv preprint arXiv:2604.01618, 2026.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Tex3D: Objects as attack surfaces via adversarial 3D textures for vision-language-action models.arXiv preprint arXiv:2604.01618, 2026

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82e816bd-de5a-46b5-a5ee-ae7e88aa151d · outbound

This paper cites Lidattack: Robust black-box attack on lidar-based object detection.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Lidattack: Robust black-box attack on lidar-based object detection

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc75f095-0770-49b3-978a-d9ce6cb2c2f1 · outbound

This paper cites Towardsphysically-realizable adversarial attacks in embodied vision navigation.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Towardsphysically-realizable adversarial attacks in embodied vision navigation

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d3d2350-247c-4e62-8892-8bb4ac873651 · outbound

This paper cites Safemind: Benchmarking and mitigating safety risks in embodied llm agents.arXiv preprint arXiv:2509.25885, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Safemind: Benchmarking and mitigating safety risks in embodied llm agents.arXiv preprint arXiv:2509.25885, 2025

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d646946e-ca6d-4dfa-970d-257212892d6e · outbound

This paper cites Shapeshifter: Robust physical adversarial attack on faster r-cnn object detector.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Shapeshifter: Robust physical adversarial attack on faster r-cnn object detector

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e4cd320-a621-4a99-9a00-ad398484d9b7 · outbound

This paper cites Metamorph: Injecting inaudible commands into over-the-air voice controlled systems.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Metamorph: Injecting inaudible commands into over-the-air voice controlled systems

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a9f97ba-9005-4ae4-bc4d-c039ffeda039 · outbound

This paper cites Catnips: Collision avoidance through neural implicit probabilistic scenes.IEEE Transactions on Robotics (T-RO), 2024.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Catnips: Collision avoidance through neural implicit probabilistic scenes.IEEE Transactions on Robotics (T-RO), 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98162ca2-4780-4a3f-86b2-8d244f95cd2a · outbound

This paper cites SAFER-Splat: A Control Barrier Function for Safe Navigation with Online Gaussian Splatting Maps.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses SAFER-Splat: A Control Barrier Function for Safe Navigation with Online Gaussian Splatting Maps

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a1d62ae-5ebd-44dc-80be-a03f2ac189d7 · outbound

This paper cites Splat-nav: Safe real-time robot navigation in gaussian splatting maps.IEEE Transactions on Robotics (T-RO), 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Splat-nav: Safe real-time robot navigation in gaussian splatting maps.IEEE Transactions on Robotics (T-RO), 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e124d44a-2285-4c62-842f-d162b2142ba0 · outbound

This paper cites Metawave: Attackingmmwavesensingwithmeta-material-enhancedtags.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Metawave: Attackingmmwavesensingwithmeta-material-enhancedtags

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc1089ea-c5cf-4d80-bc6a-7bf15bb3bbba · outbound

This paper cites Fouhey, and Joyce Chai.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Fouhey, and Joyce Chai

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7011f80d-5af1-492a-b5d1-53b5c7819c12 · outbound

This paper cites Marnet: Backdoor attacks against cooperative multi-agent reinforcement learning.IEEE Transactions on Dependable and Secure Computing (TDSC), 2023.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Marnet: Backdoor attacks against cooperative multi-agent reinforcement learning.IEEE Transactions on Dependable and Secure Computing (TDSC), 2023

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe140c86-8ddd-4145-98a5-ac778255f2bf · outbound

This paper cites Diffusion policy attacker: Crafting adversarial attacks for diffusion- based policies.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Diffusion policy attacker: Crafting adversarial attacks for diffusion- based policies

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfe3fa2a-947d-4ceb-88da-a7bc22d5faf6 · outbound

This paper cites Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c54f00a5-7956-4953-a218-7415397c3f99 · outbound

This paper cites Devil’s whisper: A general approach for physical adversarial attacks against commercial black-box speech recognition devices.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Devil’s whisper: A general approach for physical adversarial attacks against commercial black-box speech recognition devices

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f7794a7-1040-4feb-8cd8-bc0715ad5afe · outbound

This paper cites Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6b85c10-3ca5-4cd9-b067-75352c5cbc56 · outbound

This paper cites DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58a040f3-1a22-4412-a6d7-30dba030aa64 · outbound

This paper cites HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71584592-313e-4b69-93b3-27713a6a9db2 · outbound

This paper cites Manipulation facing threats: Evaluating physical vulnerabilities in end-to-end vision language action models.arXiv preprint arXiv:2409.13174, 2024.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Manipulation facing threats: Evaluating physical vulnerabilities in end-to-end vision language action models.arXiv preprint arXiv:2409.13174, 2024

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c5a7c5-e289-46cf-bdb4-2d1e53b60d97 · outbound

This paper cites Universal adversarial attack against 3d object tracking.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Universal adversarial attack against 3d object tracking

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 678d1c7a-3f39-477f-8621-e12919c558e9 · outbound

This paper cites Black-box explainability-guided adversarial attack for 3d object tracking.IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Black-box explainability-guided adversarial attack for 3d object tracking.IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb4b3920-e727-44a4-9589-1afba20a3797 · outbound

This paper cites Physical attack on monocular depth estimation with optimal adversarial patches.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Physical attack on monocular depth estimation with optimal adversarial patches

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c31b3345-1958-47f4-831d-5d988eab8885 · outbound

This paper cites ADoPT: LiDAR Spoofing Attack Detection Based on Point-Level Temporal Consistency.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses ADoPT: LiDAR Spoofing Attack Detection Based on Point-Level Temporal Consistency

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e7c7d5f-2b71-4870-87ca-870344188008 · outbound

This paper cites Sentinet: Detecting localized universal attacks against deep learning systems.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Sentinet: Detecting localized universal attacks against deep learning systems

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e2730a3-905a-4c1a-96a7-24606cd59049 · outbound

This paper cites Gupta, Mykel J.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Gupta, Mykel J

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9b855b1-68f8-4cf8-b21b-674fb688ffcf · outbound

This paper cites Handover control for human-robot and robot-robot collaboration.Frontiers in Robotics and AI, 2021.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Handover control for human-robot and robot-robot collaboration.Frontiers in Robotics and AI, 2021

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 167d61be-9a20-4063-892e-2ff5420716bf · outbound

This paper cites Pybullet, a python module for physics simulation for games, robotics and machine learning.http://pybullet.org, 2016–2021.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Pybullet, a python module for physics simulation for games, robotics and machine learning.http://pybullet.org, 2016–2021

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7234eee3-3b92-4538-a584-3786325a2593 · outbound

This paper cites Unveiling the Stealthy Threat: Analyzing Slow Drift GPS Spoofing Attacks for Autonomous Vehicles in Urban Environments and Enabling the Resilience.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Unveiling the Stealthy Threat: Analyzing Slow Drift GPS Spoofing Attacks for Autonomous Vehicles in Urban Environments and Enabling the Resilience

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e59aaba-bdc2-44b9-af3e-163e8305fae4 · outbound

This paper cites Navsim: Data-drivennon-reactiveautonomousvehiclesimulation and benchmarking.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Navsim: Data-drivennon-reactiveautonomousvehiclesimulation and benchmarking

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fd5d916-5edf-441d-8741-595344f4a076 · outbound

This paper cites Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68911bbe-3cb3-467e-81ad-de390d30e705 · outbound

This paper cites Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 2025

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da983f2f-3592-46c2-b5b2-603697299cbb · outbound

This paper cites Learning to collide: An adaptive safety-critical scenarios generating method.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Learning to collide: An adaptive safety-critical scenarios generating method

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78916a14-065d-4d69-888f-c153e4e0ed5a · outbound

This paper cites Doan, Yingjie Lao, Peng Yang, and Ping Li.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Doan, Yingjie Lao, Peng Yang, and Ping Li

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd082a4f-d8e2-44ee-abcc-c09f3639b7f1 · outbound

This paper cites Viewfool: Evaluating the robustness of visual recognition to adversarial viewpoints.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Viewfool: Evaluating the robustness of visual recognition to adversarial viewpoints

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aca29f42-57c1-4ba9-a504-8c56e780c08f · outbound

This paper cites Carla: An open urban driving simulator.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Carla: An open urban driving simulator

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c767250-2703-47c8-a227-857ca5014c24 · outbound

This paper cites Human–robot object handover: Recent progress and future direction.Robotics, 2024.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Human–robot object handover: Recent progress and future direction.Robotics, 2024

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 602b054e-2d02-4e57-bcce-77dde3ecd453 · outbound

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

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses TRAP: Tail-aware Ranking Attack for World-Model Planning

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a9d0ca3-c15c-4bde-b007-37ffcee448f7 · outbound

This paper cites A robust multi-sensor fusion model against adversarial patch attack.Wireless Networks, 2026.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses A robust multi-sensor fusion model against adversarial patch attack.Wireless Networks, 2026

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f9b5485-f63b-40c2-906d-85ceb794a2f8 · outbound

This paper cites Drones in distress: A game-theoretic countermeasure for protecting uavs against gps spoofing.IEEE Internet of Things Journal (IoT-J), 2019.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Drones in distress: A game-theoretic countermeasure for protecting uavs against gps spoofing.IEEE Internet of Things Journal (IoT-J), 2019

Reference 80

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebc8b687-5da7-4549-992c-7ca5e03742b7 · outbound

This paper cites Robust physical-world attacks on deep learning visual classification.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Robust physical-world attacks on deep learning visual classification

Reference 81

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 042a58f3-0e26-4e62-a8eb-53802afccaf4 · outbound

This paper cites Adualantennagnssspoofingdetectorbasedonthedispersion of double difference measurements.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Adualantennagnssspoofingdetectorbasedonthedispersion of double difference measurements

Reference 82

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7688329a-e0ed-492b-b2b3-69c2ae12dc1c · outbound

This paper cites Adversarial attack on trajectory prediction for autonomous vehicles with generative adversarial networks.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Adversarial attack on trajectory prediction for autonomous vehicles with generative adversarial networks

Reference 83

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 674fdbc2-f3e9-4d5b-900c-c0e9a47fc60e · outbound

This paper cites Position: Embodied AI Requires a Privacy-Utility Trade-off.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Position: Embodied AI Requires a Privacy-Utility Trade-off

Reference 84

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59a1cfb6-8d4e-455a-900e-518933166d4d · outbound

This paper cites Pso-based black-box lane detection adversarial attack.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Pso-based black-box lane detection adversarial attack

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb13064b-0201-4f5d-bf92-ca6041b3bfe8 · outbound

This paper cites A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 189075af-3422-4a77-b702-7a361582cfae · outbound

This paper cites LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 046702aa-bd19-4192-97e4-6c6bc9272a7c · outbound

This paper cites DECREE: Detecting backdoors in pre-trained encoders.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses DECREE: Detecting backdoors in pre-trained encoders

Reference 88

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45cd9bbd-b0de-44ea-859f-4e945b680ac7 · outbound

This paper cites Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment.Nature Communications, 2021.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment.Nature Communications, 2021

Reference 89

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d41a9f0-8858-4ee5-b0c2-5dddab6483a0 · outbound

This paper cites Backdooragent: A unified framework for backdoor attacks on llm-based agents.arXiv preprint arXiv:2601.04566, 2026.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Backdooragent: A unified framework for backdoor attacks on llm-based agents.arXiv preprint arXiv:2601.04566, 2026

Reference 90

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fae9d48-6002-4fd4-bced-f2c437abe317 · outbound

This paper cites A navigation message authentication proposal for the galileo open service.NAVIGATION: Journal of the Institute of Navigation, 2016.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses A navigation message authentication proposal for the galileo open service.NAVIGATION: Journal of the Institute of Navigation, 2016

Reference 91

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d39c6f1-c7db-40ec-b9f2-118aa12b2541 · outbound

This paper cites Compliantblindhandovercontrolforhuman-robotcollaboration.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Compliantblindhandovercontrolforhuman-robotcollaboration

Reference 92

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fac8b2d-1a83-4aac-8be9-5ad9b12da815 · outbound

This paper cites an unresolved cited work.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Unresolved cited work

Reference 93

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dc40168-333e-41e9-8d65-0a6853a1cde6 · outbound

This paper cites Scenic: a language for scenario specification and data generation.Machine Learning (MLJ), 2023.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Scenic: a language for scenario specification and data generation.Machine Learning (MLJ), 2023

Reference 94

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fb2f3b1-11d6-48ef-a598-b8c8d4014a5f · outbound

This paper cites Random spoofing attack against lidar-based scan matching slam.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Random spoofing attack against lidar-based scan matching slam

Reference 95

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db385e75-44a1-47be-a38d-d99d64c3542b · outbound

This paper cites 2025 ai safety index.https://futureoflife.org/ai-safety-index-summer-2 025/, 2025.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses 2025 ai safety index.https://futureoflife.org/ai-safety-index-summer-2 025/, 2025

Reference 96

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dab03ef-76a2-4183-b129-b324921a3f6f · outbound

This paper cites Bring your own (non-robust) algorithm to solve robust mdps by estimating the worst kernel.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Bring your own (non-robust) algorithm to solve robust mdps by estimating the worst kernel

Reference 97

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7472c65-bf2e-4511-8e26-8ceddbe65ecb · outbound

This paper cites Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents

Reference 98

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18928ca0-2ce0-47ed-80a3-8c24056bf466 · outbound

This paper cites an unresolved cited work.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Unresolved cited work

Reference 99

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd31e9b9-8321-4279-971c-73641f1f3a25 · outbound

This paper cites Exploring practical acoustic transduction attacks on inertial sensors in mdof systems.IEEE Transactions on Mobile Computing, 2023.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Exploring practical acoustic transduction attacks on inertial sensors in mdof systems.IEEE Transactions on Mobile Computing, 2023

Reference 100

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers