Pith. sign in

Paper Citation Record · LEDGER

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors

As of 13 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2607.25894.

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

pith.paper-citation-record.v1
2607.25894 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T01:14:59.819915Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

66 of 66 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved66
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3313d70c-4eef-439c-b98a-48e64c51b632 · outbound

This paper cites Denoising diffusion probabilistic models,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Denoising diffusion probabilistic models,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:52.873343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:52.873343Z digest=sha256:2475faf4a93e743fa5268a8221e8799c7a577ae98331da1c8b79ba2217f22a4c

Observation b05f96a8-bae2-46c5-9076-49cc25fdf799 · outbound

This paper cites High- resolution image synthesis with latent diffusion models,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors High- resolution image synthesis with latent diffusion models,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:52.960498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:52.960498Z digest=sha256:55d9b09782ef2a511726134d546095ef155abc999ae16afbddc7e32f729145e5

Observation 62250858-20d3-48c7-b20a-45b095504791 · outbound

This paper cites Collaborative diffusion for multi-modal face generation and editing,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Collaborative diffusion for multi-modal face generation and editing,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:53.077347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:53.077347Z digest=sha256:e253f15837a3429d8e792e22273419d03a62ff5babda435096154a3aed7140bf

Observation 309b3e8b-b371-4412-ab77-4a934befe55c · outbound

This paper cites Defensive adversarial captcha: A semantics- driven framework for natural adversarial example generation,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Defensive adversarial captcha: A semantics- driven framework for natural adversarial example generation,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:53.217115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:53.217115Z digest=sha256:c7c45a98f5178bbcca78a3f6594536e1489ac6efd3ac57b645530d49eca5c3cd

Observation 9a8e2f0f-9f27-4e3c-ab81-80ad36c641f3 · outbound

This paper cites State-aware perturbation optimization for robust deep reinforcement learning,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors State-aware perturbation optimization for robust deep reinforcement learning,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:53.354334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:53.354334Z digest=sha256:fc110443504803f81f2762b66dca104e39f65211d758daa0ba1b52829f7c9e16

Observation 2c05ceaf-c0c0-4ed6-b58d-b6dd970832c6 · outbound

This paper cites LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:53.503852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:53.503852Z digest=sha256:6ff71a15374780879534240d9719fde263efa972a2bf399926e1dec5b7cd1a5d

Observation c0041a79-dc1f-4535-a9c5-1de2437608ea · outbound

This paper cites A deep learning approach to universal image manipulation detection using a new convolutional layer,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors A deep learning approach to universal image manipulation detection using a new convolutional layer,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:53.651950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:53.651950Z digest=sha256:dbb467804e54ba869be162e05d7a4c3c5f6e12ebbce21bd50fbaaa27ca9199d5

Observation 5fa34824-cd88-4e5f-9ac4-fb40e1661a1f · outbound

This paper cites Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Lan- guage Models,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Lan- guage Models,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:53.810930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:53.810930Z digest=sha256:8ca69d6bbd0b60a5cf44063f75745db779b3b0be92ca74ac300888c7304e16e3

Observation aabe1403-1485-4a48-964e-59a0e96db907 · outbound

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

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors CNN- generated images are surprisingly easy to spot... for now,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:53.958253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:53.958253Z digest=sha256:de6ad1f52249834d31a821adcd50163fb23eb06f891353ce27c2ad2e15a3df15

Observation 8410db36-1775-45e8-98d8-57d27697aa75 · outbound

This paper cites SatSense: Multi-Satellite Collaborative Framework for Spectrum Sensing,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors SatSense: Multi-Satellite Collaborative Framework for Spectrum Sensing,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:54.128290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:54.128290Z digest=sha256:e1829f42f9808a3829d66f129f80eec96149097c781b330635e731d10d81fd70

Observation 0d47eb99-20ea-479c-bd1f-c70287b9e8ff · outbound

This paper cites SUMS: Sniffing Unknown Multiband Signals under Low Sampling Rates,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors SUMS: Sniffing Unknown Multiband Signals under Low Sampling Rates,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:54.284321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:54.284321Z digest=sha256:6cc087d8ead11787c809415f541681b9d3f7b67193ceeb0e9847afc7a4353ec9

Observation 97f70a76-038f-41e6-8dfa-7e1b206fac39 · outbound

This paper cites Efficient Parallel Split Learning over Resource-Constrained Wireless Edge Networks,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Efficient Parallel Split Learning over Resource-Constrained Wireless Edge Networks,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:54.406413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:54.406413Z digest=sha256:2d47960c9d65c98ec6ad45adc650c71d72d723670b19578a10594dadefbdc5c0

Observation 898a967a-fb71-4f61-b8a4-07a9957c6dc9 · outbound

This paper cites Towards universal fake image detec- tors that generalize across generative models,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Towards universal fake image detec- tors that generalize across generative models,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:54.570527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:54.570527Z digest=sha256:e0aedd901dd399e06a71911c5333ab5c3c5463d02077f2d534f0a0084259950d

Observation 445952a6-a66e-4de9-8b9d-1bcb815ef093 · outbound

This paper cites Unionformer: Unified-learning transformer with multi-view representation for im- age manipulation detection and localization,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Unionformer: Unified-learning transformer with multi-view representation for im- age manipulation detection and localization,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:54.783662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:54.783662Z digest=sha256:c3b16dc22e3c87d47fc754621f2781550c2113d0272d3cc9d5cc7d0214976fc6

Observation e5361bb0-0306-4fcd-bae4-4c1c49eb955a · outbound

This paper cites Gapsl: A gradient-aligned parallel split learning on heterogeneous data,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Gapsl: A gradient-aligned parallel split learning on heterogeneous data,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:54.908748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:54.908748Z digest=sha256:42c93fbff42af2763d6c323defdd5c837f16a10ac8c39406271caedd7afa6374

Observation c2f55e32-437e-4b8b-8aad-e09b2ddb0049 · outbound

This paper cites Hfedmoe: Resource-aware heterogeneous federated learning with mixture-of-experts,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Hfedmoe: Resource-aware heterogeneous federated learning with mixture-of-experts,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.029329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.029329Z digest=sha256:c02fdc1342d58d80afd5e7fbef56046e4c0c46840e13713a87df677790b41cea

Observation e73113ac-7fba-4233-970c-ceee31cb0a02 · outbound

This paper cites Thinking in frequency: Face forgery detection by mining frequency-aware clues,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Thinking in frequency: Face forgery detection by mining frequency-aware clues,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.154845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.154845Z digest=sha256:8a4a9755af2bdaeea7e47f4c20315729dbf5b723c02a5a5bb639cbbf253f4e0f

Observation 71bc1562-92f1-4670-a012-ddaa1f83bf6f · outbound

This paper cites Rethinking the up- sampling operations in CNN-based generative network for generalizable 13 deepfake detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Rethinking the up- sampling operations in CNN-based generative network for generalizable 13 deepfake detection,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.268181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.268181Z digest=sha256:87bb1971914ff11ed053915c51491250d53a312d37e3431e8f762f085b87eed7

Observation 8b184278-f750-4358-a91b-6b7d1c3f3994 · outbound

This paper cites Dire for diffusion-generated image detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Dire for diffusion-generated image detection,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.394580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.394580Z digest=sha256:c8fac3f91026401e49d2027077f2720a6f656376f21a4299ad7a6f0b071f5442

Observation 1b736b46-b64b-4b64-8a03-48977e00dde6 · outbound

This paper cites LaRE 2: Latent reconstruction error based method for diffusion-generated image detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors LaRE 2: Latent reconstruction error based method for diffusion-generated image detection,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.523838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.523838Z digest=sha256:6d6833ba71fe1fbce1bb902709fb6f1a6da22ad8d335bd371d93f91a216549c3

Observation ff0614d9-f15c-4835-9de3-f1006392ce91 · outbound

This paper cites Evading Deepfake-Image Detectors with White- and Black-Box Attacks.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Evading Deepfake-Image Detectors with White- and Black-Box Attacks

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.635387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.635387Z digest=sha256:7c3e1d62f4278474238493efeed41dce876b179df8d2374a08bf3720be83dedd

Observation 9e3f7d44-2a56-4d03-9ac6-a972cd2cc514 · outbound

This paper cites Vulnerabilities in AI-generated image detection: The challenge of adversarial attacks,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Vulnerabilities in AI-generated image detection: The challenge of adversarial attacks,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.748895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.748895Z digest=sha256:6637cbd4c8c2734c7fd8a56705b7727efc70903243eef66e282a916c14eb13c6

Observation 28b7b9b7-9070-48f1-a519-ad5cfd4733aa · outbound

This paper cites Take fake as real: Realistic-like robust black-box adversarial attack to evade AIGC detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Take fake as real: Realistic-like robust black-box adversarial attack to evade AIGC detection,

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:55.875282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:55.875282Z digest=sha256:7947578418c956f416ef9737d34f4f0a615562c08db049b2fdb1bccf4425e1df

Observation cdb313c7-e367-4ea2-b5a7-9437f2e4c6e9 · outbound

This paper cites StealthDif- fusion: Towards evading diffusion forensic detection through diffusion model,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors StealthDif- fusion: Towards evading diffusion forensic detection through diffusion model,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.018537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.018537Z digest=sha256:edc8c5a364d79e5de9ca80c7dbdd211c07b9cbb3ea7b16879a86cfccab33fad1

Observation 7ed8b706-8361-4088-91a6-29c32bf7919d · outbound

This paper cites Adversarial diffusion model: Generating high quality and undetectable images from scratch,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Adversarial diffusion model: Generating high quality and undetectable images from scratch,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.188146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.188146Z digest=sha256:1fa9f6c8b703b92db89779cefb034478913ecd95a4a1c950873c86cfc8221fdf

Observation d8932938-410f-4f37-ac45-81fba6f5ef6b · outbound

This paper cites Progressive Growing of GANs for Improved Quality, Stability, and Variation.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Progressive Growing of GANs for Improved Quality, Stability, and Variation

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.344873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.344873Z digest=sha256:bb2034c40787e278d1fb617393cc180881d752d5b292cd3326574b9947cb3bfb

Observation 9eb541a9-128c-4983-a9df-cc3277c7880c · outbound

This paper cites A style-based generator architecture for generative adversarial networks,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors A style-based generator architecture for generative adversarial networks,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.446594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.446594Z digest=sha256:a0d400d4f9eb107067aa441b38ddc7bc494f8028bd8eb333d9e0340f3eaac373

Observation f7967cf4-9973-498a-a78d-da105dbca8ad · outbound

This paper cites Channel Power Gain Estimation for Terahertz Vehicle-to-Infrastructure Networks,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Channel Power Gain Estimation for Terahertz Vehicle-to-Infrastructure Networks,

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.594329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.594329Z digest=sha256:ebb279ef08986225d3e06631605d194b58e8d83a219b484a24828b240d1a28bf

Observation 8edc57f5-38de-44b8-93b0-e52e67ad987b · outbound

This paper cites Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities,

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.681415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.681415Z digest=sha256:c1c2b6cb9128e14fee267c6b382f0d573747ca2169db030f8b5ce1b4cedede84

Observation 8b4f5904-f5b6-48ea-9da2-9adc0b234747 · outbound

This paper cites CAMD: Context- aware masked distillation for general self-supervised facial representa- tion pre-training,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors CAMD: Context- aware masked distillation for general self-supervised facial representa- tion pre-training,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.738073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.738073Z digest=sha256:214a8db04ff9954cacd2c884c73a11ee816df0b76129af8cf5e18d595c11035f

Observation 940e3e46-b4cf-497f-a2ef-811d832b9190 · outbound

This paper cites Mobile edge intelligence for large language models: A contemporary survey,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Mobile edge intelligence for large language models: A contemporary survey,

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.788920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.788920Z digest=sha256:1140bc746290d8d1cc25d8c0ea679ca6041f1e68441e2fcd1f18f9c13732e4ba

Observation b0e1a346-6627-4648-9c0e-715f3c8105e9 · outbound

This paper cites HASFL: Heterogeneity- aware Split Federated Learning over Edge Computing Systems,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors HASFL: Heterogeneity- aware Split Federated Learning over Edge Computing Systems,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.870054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.870054Z digest=sha256:71e6db68bebea065913022fc18f4d60dfb0dae95929781d07a1e4c07a0083215

Observation 1e451f6a-5964-4f6a-a0b0-2c79a5bfe805 · outbound

This paper cites Global texture enhancement for fake face detection in the wild,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Global texture enhancement for fake face detection in the wild,

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:56.946488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:56.946488Z digest=sha256:90d630b8daacb10029624485a6b4bbc06e36ec8e5ee6a12f2b45c59f6226a14a

Observation cb12c98a-603f-4b02-b53e-e6ace29b161c · outbound

This paper cites Image manipulation detection by multi-view multi-scale supervision,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Image manipulation detection by multi-view multi-scale supervision,

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.106345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.106345Z digest=sha256:4ef44d57ac78176bf30cbd309bc2b2a71c97b065eca4246a2496afbb8f00ea2b

Observation f6d08d17-6dd8-4bab-8bcb-bab78de55543 · outbound

This paper cites Dual frequency branch frame- work with reconstructed sliding windows attention for AI-generated image detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Dual frequency branch frame- work with reconstructed sliding windows attention for AI-generated image detection,

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.266553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.266553Z digest=sha256:57a0f66ad668be19d3db9a363d7f7a857e9344d6d5d3e8ea5f57e81b13e78bb1

Observation cfd61d44-24ea-44e5-ac72-37745da4578c · outbound

This paper cites Frequency-aware deepfake detection: Improving generalizability through frequency space learning,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Frequency-aware deepfake detection: Improving generalizability through frequency space learning,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.514165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.514165Z digest=sha256:b5264a4dd5498235ce140adc03e7fd83f0d2e6184af9358f1209e7757723eeda

Observation 7627f607-8085-4316-bd18-1da198b39978 · outbound

This paper cites A sanity check for AI-generated image detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors A sanity check for AI-generated image detection,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.625806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.625806Z digest=sha256:0e7d88c5c433ee819f6dbbcfab58e5e28650b180c48e412ba5b2255b963198e8

Observation fdee8d83-6365-4a19-a0b7-6ab9522a2b2e · outbound

This paper cites Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.733225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.733225Z digest=sha256:09097e784ec97dbcfc5067c9e376fb38e92ae9fb9f5924ed95e42b9b164b113e

Observation 1a2ba999-3788-420e-b46a-d92e911d9513 · outbound

This paper cites IMDL-BenCo: A comprehensive benchmark and codebase for image manipulation detection & localization,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors IMDL-BenCo: A comprehensive benchmark and codebase for image manipulation detection & localization,

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.784977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.784977Z digest=sha256:912bfa18dfb701159b280004b09f29bf7b6a0d2eb4b24d19c2da2f820aeda28f

Observation 4f0d7043-a722-45fb-b6b7-0a91432fb798 · outbound

This paper cites ForensicHub: A unified benchmark & codebase for all-domain fake image detection and localization,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors ForensicHub: A unified benchmark & codebase for all-domain fake image detection and localization,

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.861820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.861820Z digest=sha256:f427b66f5e7470dee33819dbddf6b0ef6cfa264c1daf394b881ae89173a5f9f1

Observation 1f29a543-913e-40b0-9934-fe222c1470ad · outbound

This paper cites Is artificial intelligence generated image detection a solved problem?.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Is artificial intelligence generated image detection a solved problem?

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:57.965474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:57.965474Z digest=sha256:de4a11e8f31d6eab63ec467107f14df1605b707aa6e7944260e8a89ed2416e3f

Observation 7341d947-bff0-4e9e-9f18-db82e2b9f4ea · outbound

This paper cites Genimage: A million-scale benchmark for detecting AI- generated image,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Genimage: A million-scale benchmark for detecting AI- generated image,

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.023163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.023163Z digest=sha256:74935b113c2929fe370942e647e934dbc726eb8723afbc23739066c3bdcb36ae

Observation 3b845410-ad3f-4dfc-81a3-2eff5ab618f1 · outbound

This paper cites Revisiting image manipulation localization under realistic manipulation scenarios,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Revisiting image manipulation localization under realistic manipulation scenarios,

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.064921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.064921Z digest=sha256:bc614ccbb39a286a47609dc1c922d38d22576a4e806808d76845df9c9e06f02f

Observation dfc2e0b4-ea3b-47c6-bec5-f6876e7fa2c4 · outbound

This paper cites AEROBLADE: Training-free detection of latent diffusion images using autoencoder reconstruction error,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors AEROBLADE: Training-free detection of latent diffusion images using autoencoder reconstruction error,

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.137456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.137456Z digest=sha256:f53f4c30f3f7adc14edd07b61f9b55e5367e7e7ab93bfc361eb98d22fd2cd87d

Observation af0c66a5-d6cd-4a04-98a9-3e4aeb32891e · outbound

This paper cites DRCT: Diffusion reconstruction contrastive training towards universal detection of diffusion generated images,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors DRCT: Diffusion reconstruction contrastive training towards universal detection of diffusion generated images,

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.220471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.220471Z digest=sha256:29f6ed10b7a2f222ac1f7304a22b5726960d4b2092d868a9bf5a949efe03fc33

Observation e663a541-a34a-4d66-be57-03c8575ea3c5 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Explaining and Harnessing Adversarial Examples

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.292084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.292084Z digest=sha256:b55045a270561dcb142604d62bd803e67d617e527f1f406558a6fe7f0ffa1d28

Observation e298c498-9e13-49a4-aeb0-ff275c2dc357 · outbound

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

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Towards deep learning models resistant to adversarial attacks,

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.373605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.373605Z digest=sha256:6c71c19a327aa0b661d0832398446c09a895faf7f35b439e57e3b27ca8a7cb19

Observation 16affd31-bbb6-4470-8e2f-2c8e5aec9b24 · outbound

This paper cites Towards evaluating the robustness of neural networks,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Towards evaluating the robustness of neural networks,

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.448871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.448871Z digest=sha256:2c7e6e006ab790b56cd9d44598c35c63573d00552f2e608a8b0f245b9d2cfe52

Observation 37638f85-a2f7-4a80-b1f0-aa778b7da28f · outbound

This paper cites Practical black-box attacks against machine learning,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Practical black-box attacks against machine learning,

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.530470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.530470Z digest=sha256:aa7f34fbb79d9af7846dd00d89e8780a23ef412bd4f589cfac6b9e4fd59cc055

Observation 6fcb1b64-9fc4-433b-9987-886374c66556 · outbound

This paper cites Boosting adversarial attacks with momentum,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Boosting adversarial attacks with momentum,

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.586193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.586193Z digest=sha256:890e2a8a6473c3c5ae9af9f05aed4b99150783ca6352773b4a9cdbe2579fb88d

Observation 1d270d0e-c7dc-49e1-8316-bb82df3b08a8 · outbound

This paper cites Simple black-box adversarial attacks,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Simple black-box adversarial attacks,

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.653436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.653436Z digest=sha256:e36a95b2ff4342359c9bbd37d104bc70a6e8b2bf6f0a93dfe0808bfeeea06d12

Observation 2ab1a43e-a8c0-471e-ab76-c69cb2afdbb6 · outbound

This paper cites Square at- tack: A query-efficient black-box adversarial attack via random search,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Square at- tack: A query-efficient black-box adversarial attack via random search,

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.755797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.755797Z digest=sha256:bf35201a160ffb3119247bb5a0485ab1307ff3bd1fc8e47edc77e6b39deb767d

Observation 27068082-94fb-413f-a8b7-97a676b6d274 · outbound

This paper cites BRUSLEATTACK: A query-efficient score-based black-box sparse adversarial attack,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors BRUSLEATTACK: A query-efficient score-based black-box sparse adversarial attack,

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.837882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.837882Z digest=sha256:3a15a50edb0c7321b0b3a1d8e2ef4304d43c325926bd086b59c059552c6748d6

Observation d3343a69-ae63-46b9-a966-9ac15918b0c6 · outbound

This paper cites DP-RAE: A dual-phase merging reversible adversarial example for image privacy protection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors DP-RAE: A dual-phase merging reversible adversarial example for image privacy protection,

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.917194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.917194Z digest=sha256:9fc48e39f2ad50c7f03995c80749ce5c1891171a28bd3edbaaf92381c51ffb0c

Observation e28c1453-77a6-4fd4-9c24-6d94c1178060 · outbound

This paper cites Guided evolutionary strategies: Augmenting random search with surrogate gradients,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Guided evolutionary strategies: Augmenting random search with surrogate gradients,

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:58.995988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:58.995988Z digest=sha256:46e2a9a4e82c73cdefe9c3b56ecfa169e08852d13af4b30419508073ffb7a513

Observation 846632fb-a8f1-49fb-ad53-b8d7ca2c5f05 · outbound

This paper cites Improving black- box adversarial attacks with a transfer-based prior,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Improving black- box adversarial attacks with a transfer-based prior,

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.077293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.077293Z digest=sha256:5e92ed118c5124fab87bc1ae9b2394329d23b74df2e8662613d1304768fbc89f

Observation e5389de8-ef75-4f27-a2bb-b085aa08b3f7 · outbound

This paper cites Adversarial Deepfakes: Evaluating vulnerability of Deepfake detectors to adversarial examples,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Adversarial Deepfakes: Evaluating vulnerability of Deepfake detectors to adversarial examples,

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.145301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.145301Z digest=sha256:d145662566b751e0824ad9f697d68052ccdfacf21481a1cb6650b8b21d3ddf97

Observation 4e5185ba-5501-44b6-a314-4ec679beaa80 · outbound

This paper cites Evading Deep- fake detectors via adversarial statistical consistency,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Evading Deep- fake detectors via adversarial statistical consistency,

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.194927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.194927Z digest=sha256:19ecd9d18fac6a69edb1cb61d10b1b13a42502bcfecbcdfbf78f41af8d181fba

Observation 632520a5-a857-4e74-8bc6-5a63896131b2 · outbound

This paper cites MaskGAN: Towards diverse and interactive facial image manipulation,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors MaskGAN: Towards diverse and interactive facial image manipulation,

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.236911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.236911Z digest=sha256:a72502d667bc32265c5d20ade1bd752a726870bb6d11d025e1019faef605b4ca

Observation 96894722-f037-4cda-976c-dfd645f5bf8e · outbound

This paper cites Deep residual learning for image recognition,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Deep residual learning for image recognition,

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.280156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.280156Z digest=sha256:8953c9ea33827279f534c6f36ba284345625bca95235a60a4815e71870add980

Observation 419af507-011a-48fc-871d-7b06be3aa731 · outbound

This paper cites EfficientNet: Rethinking model scaling for con- volutional neural networks,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors EfficientNet: Rethinking model scaling for con- volutional neural networks,

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.283406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.283406Z digest=sha256:cbcf643cd26c33deb70a5f6adb47be27078dd68abcf6006aafb33e25c36eff1b

Observation 3d872d4a-38ca-4d53-927b-fad8b5f2e69e · outbound

This paper cites Training data-efficient image transformers & distillation through attention,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Training data-efficient image transformers & distillation through attention,

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.293188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.293188Z digest=sha256:c0cbd6b465baf1716c5e6e0b2b2f033e660665e0a65726a4a1b67ef4d8a5f00d

Observation 1c2221f1-38d3-48f1-998e-99de748e65d0 · outbound

This paper cites Swin Transformer: Hierarchical vision transformer using shifted win- dows,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Swin Transformer: Hierarchical vision transformer using shifted win- dows,

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.436491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.436491Z digest=sha256:9b4d02661e1808d84111ee7f657ec29232fcafa7d0dee5fb7abb3a4265885823

Observation d5796985-65e1-40c0-9274-6936951563e5 · outbound

This paper cites Orthogonal subspace decomposition for generalizable AI-generated image detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors Orthogonal subspace decomposition for generalizable AI-generated image detection,

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.592071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.592071Z digest=sha256:ffbce2b9df5086f1e0fb8280ee25a16629e67222a6d7c8c1f4f157a66dc37150

Observation 490c3afb-b17f-414c-b066-2983915a4996 · outbound

This paper cites PGC: Peak-guided calibration for generalizable AI-generated image detection,.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors PGC: Peak-guided calibration for generalizable AI-generated image detection,

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.819915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.819915Z digest=sha256:d3a06bc2694157c04e2e25425b3a4321d699dc0a9417eb10aae994e0aa4e2d27

Observation e38d0f9a-bc2c-4ec9-a934-41e3b9bc37aa · outbound

This paper cites 70 268–70 288.

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors 70 268–70 288

Reference 267

Resolution
unresolved
no resolver link, observed 2026-08-01T01:14:59.661794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:14:59.661794Z digest=sha256:46dabbad2d42f8a717fde3d6dccb7af2b81f7236e17560e0bf4f9175215beb05

Pith citing papers

No inbound Pith citation observations are available.