Paper Citation Record · LEDGER

Antelope: Potent and Concealed Jailbreak Attack Strategy

As of 16 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2412.08156.

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

pith.paper-citation-record.v1
2412.08156 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T18:14:48.210139Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

45 of 45 outbound references displayed

verified exact0
verified fuzzy32
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 93e12c1d-757f-442a-9f5e-0ae7a7027d6d · outbound

This paper cites Improving image gener- ation with better captions, 2023.

Antelope: Potent and Concealed Jailbreak Attack Strategy Improving image gener- ation with better captions, 2023

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.786795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2b704b33-7132-4d0f-b7d5-fa4b5425fdad · outbound

This paper cites an unresolved cited work.

Antelope: Potent and Concealed Jailbreak Attack Strategy Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-11T18:14:48.773557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7e9f3173-975d-49ba-a6c5-014bf1e8d088 · outbound

This paper cites Con- ceptprune: Concept editing in diffusion models via skilled neuron pruning, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Con- ceptprune: Concept editing in diffusion models via skilled neuron pruning, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.761114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 23670e61-1334-46a7-b11a-0f309003fca1 · outbound

This paper cites How to backdoor diffusion models? In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4015–4024, 2023.

Antelope: Potent and Concealed Jailbreak Attack Strategy How to backdoor diffusion models? In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4015–4024, 2023

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.749005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 23e9082c-455e-44d3-a91f-1d935c287a2d · outbound

This paper cites Divide-and-conquer at- tack: Harnessing the power of llm to bypass safety filters of text-to-image models, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Divide-and-conquer at- tack: Harnessing the power of llm to bypass safety filters of text-to-image models, 2024

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.736664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 917aa238-04ae-4333-8e9b-ab7529349115 · outbound

This paper cites BERT: Pre-training of deep bidirectional trans- formers for language understanding.

Antelope: Potent and Concealed Jailbreak Attack Strategy BERT: Pre-training of deep bidirectional trans- formers for language understanding

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.723898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d7fc3e2f-d7a1-4ae2-a1cd-e271c15c49c4 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale, 2021.

Antelope: Potent and Concealed Jailbreak Attack Strategy An image is worth 16x16 words: Transformers for image recognition at scale, 2021

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:47.783264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a56a9630-25cc-42cb-b34b-89a208257fa6 · outbound

This paper cites Erasing concepts from diffusion models.

Antelope: Potent and Concealed Jailbreak Attack Strategy Erasing concepts from diffusion models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.705056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 70438ef6-ca70-4931-8a52-e0e028907385 · outbound

This paper cites Rt-attack: Jailbreaking text-to-image models via random token, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Rt-attack: Jailbreaking text-to-image models via random token, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.693886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d4412a27-56be-4bf5-9d1f-8d0c07443eec · outbound

This paper cites Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation.

Antelope: Potent and Concealed Jailbreak Attack Strategy Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:47.795435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d012268-aafd-4778-8134-e8699c0ba8f0 · outbound

This paper cites Denoising Diffusion Probabilistic Models.

Antelope: Potent and Concealed Jailbreak Attack Strategy Denoising Diffusion Probabilistic Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:47.810197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc478466-c0c9-405d-aacc-ea3c897b8ecd · outbound

This paper cites Perception-guided jailbreak against text-to-image models, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Perception-guided jailbreak against text-to-image models, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.682586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9ef77bcc-f99d-46cb-bf78-3077a9b48c66 · outbound

This paper cites Inappropriate image prompts.

Antelope: Potent and Concealed Jailbreak Attack Strategy Inappropriate image prompts

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.669230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 24cb623d-43fa-43cf-868a-5ae0bf776212 · outbound

This paper cites Leonardo.ai, 2023.

Antelope: Potent and Concealed Jailbreak Attack Strategy Leonardo.ai, 2023

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.656751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4bc4cb9e-1d55-4d39-bafa-52c08aee17bc · outbound

This paper cites SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models.

Antelope: Potent and Concealed Jailbreak Attack Strategy SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:47.881865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cba9fce-43f9-45be-9def-a84be8d098f9 · outbound

This paper cites Groot: Adversarial testing for generative text-to-image models with tree-based semantic transformation, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Groot: Adversarial testing for generative text-to-image models with tree-based semantic transformation, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.645247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4a40ef8c-0ab8-4349-9c43-ce36ec596445 · outbound

This paper cites Jailbreaking prompt attack: A controllable adversarial attack against diffusion models, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Jailbreaking prompt attack: A controllable adversarial attack against diffusion models, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.632681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bd561369-95ac-44e1-b14e-ed4a86e97075 · outbound

This paper cites Towards deep learning models resistant to adversarial attacks, 2019.

Antelope: Potent and Concealed Jailbreak Attack Strategy Towards deep learning models resistant to adversarial attacks, 2019

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.617913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ed2f4069-5950-4df1-b9cd-4d405c506030 · outbound

This paper cites Generating images from captions with attention, 2016.

Antelope: Potent and Concealed Jailbreak Attack Strategy Generating images from captions with attention, 2016

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.605271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 00799132-53ee-46a7-a8c1-d8372da594e0 · outbound

This paper cites Midjourney, 2023.

Antelope: Potent and Concealed Jailbreak Attack Strategy Midjourney, 2023

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.592153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 014760c4-0097-4e77-8e6b-ffc45035101c · outbound

This paper cites GLIDE: towards photorealis- tic image generation and editing with text-guided diffusion models.

Antelope: Potent and Concealed Jailbreak Attack Strategy GLIDE: towards photorealis- tic image generation and editing with text-guided diffusion models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.580458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0da00477-1b26-4726-a2ce-3f5002819494 · outbound

This paper cites an unresolved cited work.

Antelope: Potent and Concealed Jailbreak Attack Strategy Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-11T18:14:48.568062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a75c5483-a379-4815-9c46-fe53f2fa7208 · outbound

This paper cites Chatgpt, 2023.

Antelope: Potent and Concealed Jailbreak Attack Strategy Chatgpt, 2023

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.556927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b15ea080-8c6f-42ce-b395-810884ce1672 · outbound

This paper cites Scalable Diffusion Models with Transformers.

Antelope: Potent and Concealed Jailbreak Attack Strategy Scalable Diffusion Models with Transformers

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:47.917337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdb3d474-fe56-4176-8673-48f5c7faeddb · outbound

This paper cites Upam: Unified prompt attack in text-to-image generation models against both tex- tual filters and visual checkers, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Upam: Unified prompt attack in text-to-image generation models against both tex- tual filters and visual checkers, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.544698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d17cbd50-5b5e-4be9-918f-0bcc80af6c5c · outbound

This paper cites Unsafe diffusion: On the generation of unsafe images and hateful memes from text- to-image models, 2023.

Antelope: Potent and Concealed Jailbreak Attack Strategy Unsafe diffusion: On the generation of unsafe images and hateful memes from text- to-image models, 2023

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.532742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 769a4e79-adfc-47ad-a4b7-1ade859191f1 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Antelope: Potent and Concealed Jailbreak Attack Strategy Learning transferable visual models from natural language supervision

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:47.958066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ef0170b-7334-463a-b4b8-137b7f7bc205 · outbound

This paper cites Zero-shot text-to-image generation.

Antelope: Potent and Concealed Jailbreak Attack Strategy Zero-shot text-to-image generation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.511859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f866b547-e378-4590-a371-a8355ea1e0ad · outbound

This paper cites Hierarchical text-conditional image gener- ation with clip latents, 2022.

Antelope: Potent and Concealed Jailbreak Attack Strategy Hierarchical text-conditional image gener- ation with clip latents, 2022

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.498035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c104cd2b-7db6-4cd9-a456-752e5ba4d1a6 · outbound

This paper cites Red-teaming the stable diffusion safety filter, 2022.

Antelope: Potent and Concealed Jailbreak Attack Strategy Red-teaming the stable diffusion safety filter, 2022

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.484785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d82fe8af-81a8-4050-bede-bb2dbc7771b0 · outbound

This paper cites High-resolution image syn- thesis with latent diffusion models.

Antelope: Potent and Concealed Jailbreak Attack Strategy High-resolution image syn- thesis with latent diffusion models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.471737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2e42ddae-78ed-4324-a47a-6836b054bab9 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation,.

Antelope: Potent and Concealed Jailbreak Attack Strategy U-net: Convolutional networks for biomedical image segmentation,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:48.098254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4fbfb67-c6a1-4552-aa2e-669946ec4b68 · outbound

This paper cites an unresolved cited work.

Antelope: Potent and Concealed Jailbreak Attack Strategy Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-11T18:14:48.451393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 024f2fb7-32dc-4c1b-a894-cd4e1cca60b0 · outbound

This paper cites Safe latent diffusion: Mitigating inappro- priate degeneration in diffusion models, 2023.

Antelope: Potent and Concealed Jailbreak Attack Strategy Safe latent diffusion: Mitigating inappro- priate degeneration in diffusion models, 2023

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.436408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bf94ca88-7212-4e4c-a9a8-c6d86d9d5794 · outbound

This paper cites Denoising Diffusion Implicit Models.

Antelope: Potent and Concealed Jailbreak Attack Strategy Denoising Diffusion Implicit Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:48.160237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4ad04a3-9194-41ca-9867-839d254a10a0 · outbound

This paper cites Ring-a-bell! how reliable are concept removal meth- ods for diffusion models?, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Ring-a-bell! how reliable are concept removal meth- ods for diffusion models?, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.422292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5cfd9aab-f5dc-4eb2-9f4e-016fe23758e9 · outbound

This paper cites Attention Is All You Need.

Antelope: Potent and Concealed Jailbreak Attack Strategy Attention Is All You Need

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:48.170198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2c62a16-c53e-44ac-96ee-e3025251222c · outbound

This paper cites On the multi-modal vulnera- bility of diffusion models.

Antelope: Potent and Concealed Jailbreak Attack Strategy On the multi-modal vulnera- bility of diffusion models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.408872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 017c60d7-3787-45cd-b10c-eb2a3344c93b · outbound

This paper cites Mma-diffusion: Multimodal at- tack on diffusion models.

Antelope: Potent and Concealed Jailbreak Attack Strategy Mma-diffusion: Multimodal at- tack on diffusion models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.396007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d572b07d-5818-418d-ae49-75ac9957cd4c · outbound

This paper cites Guardt2i: Defending text-to-image models from adversarial prompts, 2024.

Antelope: Potent and Concealed Jailbreak Attack Strategy Guardt2i: Defending text-to-image models from adversarial prompts, 2024

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.382994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4f83f497-f747-4eaa-9f4f-07c28db11ab2 · outbound

This paper cites Sneakyprompt: Jailbreaking text-to-image generative models.

Antelope: Potent and Concealed Jailbreak Attack Strategy Sneakyprompt: Jailbreaking text-to-image generative models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.369784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b7eb525b-cae4-4421-a3bc-0a24b24c1d04 · outbound

This paper cites Vector-quantized Image Modeling with Improved VQGAN.

Antelope: Potent and Concealed Jailbreak Attack Strategy Vector-quantized Image Modeling with Improved VQGAN

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T18:14:48.193392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a3975fd-1ce8-4273-aabc-ed9feb0789ea · outbound

This paper cites To gener- ate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images.

Antelope: Potent and Concealed Jailbreak Attack Strategy To gener- ate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.357130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f3be4cf8-ba9f-4d43-9960-062bde8a40e0 · outbound

This paper cites Cipherdm: Secure three-party infer- ence for diffusion model sampling.

Antelope: Potent and Concealed Jailbreak Attack Strategy Cipherdm: Secure three-party infer- ence for diffusion model sampling

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.343996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c41ccd53-30a8-4937-841f-0b67a78db71f · outbound

This paper cites A pilot study of query-free adversarial attack against stable diffusion.

Antelope: Potent and Concealed Jailbreak Attack Strategy A pilot study of query-free adversarial attack against stable diffusion

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:14:48.330414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.