Paper Citation Record · LEDGER

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks

As of 13 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2505.23192.

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

pith.paper-citation-record.v1
2505.23192 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:56:20.846056Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

18 of 18 outbound references displayed

verified exact1
verified fuzzy5
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ca1f379d-283b-4e2c-9860-dc8fb3fa589a · outbound

This paper cites Accessed: 2025-05-18.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Accessed: 2025-05-18

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:56:23.107961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6a545282-2bfa-41b1-aba6-437743548b31 · outbound

This paper cites midjourney.com/home/.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks midjourney.com/home/

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:56:22.942382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cda8b0a4-ce53-4915-967a-c0b8628024b6 · outbound

This paper cites Scaling up GANs for Text-to-Image Synthesis.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Scaling up GANs for Text-to-Image Synthesis

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:19.939101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 923f531e-7672-49c6-9807-dc9b2d9bfdb8 · outbound

This paper cites AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:56:21.767902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d4172971-c50e-4ceb-8905-4e0680e55608 · outbound

This paper cites GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:20.129661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd25414-fe52-4f99-a175-673c194ba363 · outbound

This paper cites Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:20.210783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc1e6bf9-d1c3-47f8-b054-dfd741258539 · outbound

This paper cites Tencent zhuque lab.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Tencent zhuque lab

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:56:22.709161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 69be407b-9920-4cf3-ac00-16e30c2c87d8 · outbound

This paper cites Tian, B., Juefei-Xu, F., Guo, Q., Xie, X., Li, X., and Liu, Y.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Tian, B., Juefei-Xu, F., Guo, Q., Xie, X., Li, X., and Liu, Y

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:56:22.484071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 55f0ce80-d637-4fe8-b1c5-9529318fa8d2 · outbound

This paper cites BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:56:21.367074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f5a718e4-7c80-41af-b5ca-581dd64aac76 · outbound

This paper cites CNN-generated images are surprisingly easy to spot... for now.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks CNN-generated images are surprisingly easy to spot... for now

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:20.666880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c8f9b3-ce7e-4c79-9da0-6f3cac1d0df0 · outbound

This paper cites Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:56:21.058197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 321008e4-ca8b-4214-9d6b-f782f000af00 · outbound

This paper cites PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:20.846056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece8af2b-dd95-45b5-a94e-5e219958e9a9 · outbound

This paper cites Douglas, J.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Douglas, J

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:19.497002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ebd3238-2530-4c20-823b-b725dc18440a · outbound

This paper cites Square Attack: a query-efficient black-box adversarial attack via random search.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Square Attack: a query-efficient black-box adversarial attack via random search

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:19.331876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471b452d-8d12-4539-9f45-d4c2dc9ed16b · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks LoRA: Low-Rank Adaptation of Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:19.738216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba66880b-1ada-41ca-a685-34dfbb48cb14 · outbound

This paper cites Evading Watermark based Detection of AI-Generated Content.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Evading Watermark based Detection of AI-Generated Content

Reference 2023

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:56:22.128118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 50f23b56-b595-45ea-9614-f07fcfd25899 · outbound

This paper cites WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T12:56:19.677840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4eaa1a1-5988-44ce-b6b5-fe016506df6d · outbound

This paper cites Andriushchenko, M., Croce, F., Flammarion, N., and Hein, M.

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks Andriushchenko, M., Croce, F., Flammarion, N., and Hein, M

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:56:23.339620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.