SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense | Paper Citation Record

Observation 3621170c-3fdd-46e2-80f0-fc40c4eed616 · outbound

This paper cites luma dream machine, 2024.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense luma dream machine, 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.862468Z

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 ec10b06b-8c33-4795-9427-3d480ba6238c · outbound

This paper cites Frozen in time: A joint video and image encoder for end-to-end retrieval, 2021.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Frozen in time: A joint video and image encoder for end-to-end retrieval, 2021

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.841263Z

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 3b67e2fa-adaa-4280-968c-b8d964b66e78 · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.263970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00a8dc0-52d0-42c0-b2e2-9dc01d3ef0d5 · outbound

This paper cites Transformer Interpretability Beyond Attention Visualization.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Transformer Interpretability Beyond Attention Visualization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.272247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3207e168-661f-4923-8765-b9c2cd0cbc9d · outbound

This paper cites Transformer inter- pretability beyond attention visualization.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Transformer inter- pretability beyond attention visualization

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.820844Z

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 dd18a8dc-8fa7-41f5-b1ef-592bd7b2418c · outbound

This paper cites Videocrafter2: Overcoming data limitations for high-quality video diffu- sion models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Videocrafter2: Overcoming data limitations for high-quality video diffu- sion models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.793770Z

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 1b194c8a-90e4-44d1-8fbb-0dd988a485f4 · outbound

This paper cites SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.294275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d9cfe28-841e-4496-95dc-fa4bf40d3c83 · outbound

This paper cites Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.299903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fd487d9-3984-4e6c-ac3f-90d1a8f2657f · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated ap- plications with indirect prompt injection.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Not what you’ve signed up for: Compromising real-world llm-integrated ap- plications with indirect prompt injection

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.776223Z

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 c215ba6d-439a-4854-91f7-b8745555ad68 · outbound

This paper cites Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.313665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a3a2b8-8ce7-42e6-a674-8a2e9f4cc013 · outbound

This paper cites NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-12T14:01:42.378552Z

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 4c4bc3a6-4452-4519-b453-f790865937f6 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.329399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8972b9cb-ce23-4fc2-97e7-a8a31332e2be · outbound

This paper cites CogMorph: Cognitive Morphing Attacks for Text-to-Image Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense CogMorph: Cognitive Morphing Attacks for Text-to-Image Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.335157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b9dec2-e8b1-4543-a0d5-68eeb5a64972 · outbound

This paper cites VideoPoet: A Large Language Model for Zero-Shot Video Generation.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense VideoPoet: A Large Language Model for Zero-Shot Video Generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.341437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43710e97-8d7a-4c1e-a991-9ea39212dba6 · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.348391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d353691-0f5f-4120-91bc-cef5f852c683 · outbound

This paper cites Bridg- ing text and video generation: A survey.arXiv preprint arXiv:2510.04999, 2025.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Bridg- ing text and video generation: A survey.arXiv preprint arXiv:2510.04999, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.354134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd25bb91-9d8f-4890-b3c5-17aa88224f50 · outbound

This paper cites Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.360266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f784ee13-bc4b-41fc-a28e-37dd8c9be12e · outbound

This paper cites SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.366538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d734b093-3c1e-468d-b241-58ca493f5254 · outbound

This paper cites Exploring inconsistent knowledge distil- lation for object detection with data augmentation.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Exploring inconsistent knowledge distil- lation for object detection with data augmentation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.753162Z

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 acb65aa9-fd16-4785-9da7-5838883f6ecd · outbound

This paper cites A large-scale multiple- objective method for black-box attack against object detec- tion.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense A large-scale multiple- objective method for black-box attack against object detec- tion

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.734396Z

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 aa3512d5-d9fd-465e-a773-0bed35cd8693 · outbound

This paper cites Imitated detectors: Stealing knowl- edge of black-box object detectors.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Imitated detectors: Stealing knowl- edge of black-box object detectors

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.716384Z

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 5997afa1-715b-4658-93ed-45fe0e387139 · outbound

This paper cites Badclip: Dual- embedding guided backdoor attack on multimodal con- trastive learning.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Badclip: Dual- embedding guided backdoor attack on multimodal con- trastive learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.694850Z

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 03be24ac-c4ba-4923-95eb-0e8b77dbb5cb · outbound

This paper cites Re- visiting backdoor attacks against large vision-language mod- els from domain shift.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Re- visiting backdoor attacks against large vision-language mod- els from domain shift

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.675758Z

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 75b6184d-628f-4045-8014-aa06a4e4f31a · outbound

This paper cites T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.409683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c1450e-a640-44d9-a75a-f765678b4c7b · outbound

This paper cites T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.416164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b37bf1e9-2c04-4f9a-bdb1-6d6a0da3e612 · outbound

This paper cites Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.421711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3430bbff-3f71-4fc1-9474-13c77bfbd341 · outbound

This paper cites T2vsafetybench: Evaluating the safety of text-to-video generative models.Advances in Neural In- formation Processing Systems, 37:63858–63872, 2024.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense T2vsafetybench: Evaluating the safety of text-to-video generative models.Advances in Neural In- formation Processing Systems, 37:63858–63872, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.651236Z

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 9cbb6cf0-a596-4ec5-808f-38138c7904fb · outbound

This paper cites OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.432312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ebe9aa-8a0d-474c-b5f6-506e679252c8 · outbound

This paper cites T2veval: Benchmark dataset and objective evaluation method for t2v-generated videos.Displays, page 103178,.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense T2veval: Benchmark dataset and objective evaluation method for t2v-generated videos.Displays, page 103178,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.634346Z

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 9085880b-0bed-4c4d-871b-ad881d48e851 · outbound

This paper cites Make-A-Video: Text-to-Video Generation without Text-Video Data.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Make-A-Video: Text-to-Video Generation without Text-Video Data

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.446099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91185768-7cf0-4da1-a1a5-4580ab734650 · outbound

This paper cites Kling-omni technical report, 2025.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Kling-omni technical report, 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.618604Z

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 787ac11e-2afb-4b10-959c-eebed3a757ad · outbound

This paper cites Videotetris: Towards compositional text-to-video generation.Advances in Neural Information Processing Sys- tems, 37:29489–29513, 2024.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Videotetris: Towards compositional text-to-video generation.Advances in Neural Information Processing Sys- tems, 37:29489–29513, 2024

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.602757Z

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 aa6d094c-6ecd-415f-a8a3-05a3584c3702 · outbound

This paper cites Manipulating Multimodal Agents via Cross-Modal Prompt Injection.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.462806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f40b8f3-844b-41c1-9968-e5b0f8480707 · outbound

This paper cites Jail- broken: How does llm safety training fail?Advances in neu- ral information processing systems, 36:80079–80110, 2023.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Jail- broken: How does llm safety training fail?Advances in neu- ral information processing systems, 36:80079–80110, 2023

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.583597Z

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 fc4eeec0-dd76-452b-abce-c1d7f2013989 · outbound

This paper cites Defensive prompt patch: A robust and generalizable defense of large language models against jailbreak attacks.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Defensive prompt patch: A robust and generalizable defense of large language models against jailbreak attacks

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.560545Z

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 532d45e4-ee0e-4995-a0ca-a53616ba061a · outbound

This paper cites Video- eraser: Concept erasure in text-to-video diffusion models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Video- eraser: Concept erasure in text-to-video diffusion models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.541646Z

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 6b4a4a8d-21e5-42fe-a6fa-0d08d8f668dd · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.500641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a610f3-d5d9-4ea5-a11e-e2d4588ba948 · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.509428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62a1afb1-8ef7-4f5d-9bd2-81bbc9236c81 · outbound

This paper cites Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.516193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a84e0f-5891-4928-8125-6b618b3d553f · outbound

This paper cites Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.521564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd8eaec9-7540-4b66-b0ff-cf4653a68eb6 · outbound

This paper cites Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.527677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d33333d5-1b61-4c26-b77e-7a84afc3ae10 · outbound

This paper cites SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.533067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab41e49-4e0a-42f6-bcc1-bdcd5fa9660a · outbound

This paper cites Safree: Training-free and adaptive guard for safe text-to-image and video generation.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Safree: Training-free and adaptive guard for safe text-to-image and video generation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.522597Z

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 c100e2ec-4c37-49f1-bdfa-be661290bb15 · outbound

This paper cites Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.549719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19624e28-881f-42bb-964d-0cfc1773be5d · outbound

This paper cites BadRobot: Jailbreaking Embodied LLM Agents in the Physical World.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.556081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e47367e-6738-42a7-9a3e-be9d00ec226c · outbound

This paper cites Jbshield: Defending large lan- guage models from jailbreak attacks through activated con- cept analysis and manipulation.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Jbshield: Defending large lan- guage models from jailbreak attacks through activated con- cept analysis and manipulation

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:01:42.503946Z

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 9f387c79-6dd8-4fdd-9df1-3c138f0b56fd · outbound

This paper cites Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.567414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fa8f2b4-2334-4a8e-bc4d-9c924c6f477b · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Open-Sora: Democratizing Efficient Video Production for All

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.585415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 827e0253-8a58-4128-9d07-a5c44328da0a · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T14:01:41.590694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers