Pith. sign in

Paper Citation Record · LEDGER

LLMs Are Not Yet Ready for Deepfake Image Detection

As of 14 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 4 inbound Pith citation observations for arXiv:2506.10474.

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

pith.paper-citation-record.v1
2506.10474 v1

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:32:25.888929Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:08:54.359370Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T10:39:45.171543Z

Reference resolution

56 of 56 outbound references displayed

  • verified exact1
  • verified fuzzy46
  • unresolved9
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 166ad18b-de37-487b-8402-2a3022969c3a · outbound

This paper cites Deepfakes and stolen pii utilized to apply for remote work positions.

LLMs Are Not Yet Ready for Deepfake Image Detection Deepfakes and stolen pii utilized to apply for remote work positions

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.253711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.457524Z digest=sha256:8a56925e5ce045ada015b478e6c49fed9cd7ac27781bca0d487801ba8c40397d

Observation dba18f95-af0b-4ffe-a8b3-92f496c55dc2 · outbound

This paper cites Deepfake in the metaverse: Security implications for virtual gaming, meetings, and offices.

LLMs Are Not Yet Ready for Deepfake Image Detection Deepfake in the metaverse: Security implications for virtual gaming, meetings, and offices

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.244415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.546416Z digest=sha256:ca2b80215bcd62c4b1a11955b2ef74b782dc84edc8ae908c295b81a947447bb1

Observation 5767e4b2-c702-409c-ac2d-d66ecbe09d50 · outbound

This paper cites an unresolved cited work.

LLMs Are Not Yet Ready for Deepfake Image Detection Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-07T04:32:32.235081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.621090Z digest=sha256:0c2cf7a68cdeca2cdecb24975125d1ab7a5c443634c98fb9dd8f3e82ee8500fd

Observation 33d60394-5117-4cf7-aed1-d61eba51289c · outbound

This paper cites Classifying genuine face images from disguised face images.

LLMs Are Not Yet Ready for Deepfake Image Detection Classifying genuine face images from disguised face images

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.226215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.675493Z digest=sha256:0012faa02a32f29dec9ed563193631cdc8977361920a1d2990342d225f941ec4

Observation 58c40b11-08e8-44d0-9cad-7a08b5830be2 · outbound

This paper cites Seeing is living? rethinking the security of facial liveness verification in the deepfake era.

LLMs Are Not Yet Ready for Deepfake Image Detection Seeing is living? rethinking the security of facial liveness verification in the deepfake era

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.217048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.784444Z digest=sha256:57ddd54c86dae50e98992632ffeb1d652eabeacd729908aba4ada9531d0cd2f3

Observation c57fc72b-9255-4f2b-bbb0-d6870b1d7988 · outbound

This paper cites Evaluating trustworthiness and racial bias in face recognition apis using deepfakes.Computer, 56(5):51–61, 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Evaluating trustworthiness and racial bias in face recognition apis using deepfakes.Computer, 56(5):51–61, 2023

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.207554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.876499Z digest=sha256:dafd65f9b660f3a9a395129d919840744e74cb73db8f16fe9d1bd9cf8e92dcb4

Observation c13760f6-a71f-44e0-8b6a-10b271bd63d5 · outbound

This paper cites When george clooney is not george clooney: Using genattack to deceive amazon’s and naver’s celebrity recognition apis.

LLMs Are Not Yet Ready for Deepfake Image Detection When george clooney is not george clooney: Using genattack to deceive amazon’s and naver’s celebrity recognition apis

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.198240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.915659Z digest=sha256:9ca3054ad528cafc39f5c4619e21700c43eb90a389a8253628c3afabadd25c92

Observation ecc6c882-f7b9-42ab-b4f6-5277fbef87c6 · outbound

This paper cites Am i a real or fake celebrity? evaluating face recognition and verification apis under deepfake impersonation attack.

LLMs Are Not Yet Ready for Deepfake Image Detection Am i a real or fake celebrity? evaluating face recognition and verification apis under deepfake impersonation attack

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.187988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:20.988141Z digest=sha256:5e91ed1ff52fd3fcdf7de12897dc545ab044af5481114487ad7c2529522ce7e3

Observation 943e1172-668d-40e2-ada3-ce386582ee87 · outbound

This paper cites Le and Simon Woo.

LLMs Are Not Yet Ready for Deepfake Image Detection Le and Simon Woo

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.178418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:21.059899Z digest=sha256:af257f3beb716822604b858d09d712a7bb03a4de802eb6ae92617011fee90e7d

Observation 86a887b9-7ab7-42e3-947b-da453714e1f4 · outbound

This paper cites Self-supervised video forensics by audio-visual anomaly detection.

LLMs Are Not Yet Ready for Deepfake Image Detection Self-supervised video forensics by audio-visual anomaly detection

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.168920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:21.097934Z digest=sha256:7b0b3e0f9fd34301b5d0bd07fc6db2fa7f682f7571ef3de28066abbcf6b79488

Observation ca6d9360-cb1c-4902-8be8-311062c2a8f3 · outbound

This paper cites Aunet: Learning relations between action units for face forgery detection.

LLMs Are Not Yet Ready for Deepfake Image Detection Aunet: Learning relations between action units for face forgery detection

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.158833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:21.195317Z digest=sha256:0c594c9d18b3c57ed43af53f92d885a3922097fa0ee7c33ce2255bf1782049e7

Observation d0192426-d87a-488e-b550-637a6f04891d · outbound

This paper cites Capsule-forensics: Using capsule networks to detect forged images and videos.

LLMs Are Not Yet Ready for Deepfake Image Detection Capsule-forensics: Using capsule networks to detect forged images and videos

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.149324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:21.297889Z digest=sha256:743b17b60463dfdcfc25ef1ccafa39b7eacf71e6cd4e2efbdf5b742300b60dd2

Observation a7a000ea-0f61-47b2-b053-548811c385ed · outbound

This paper cites One detector to rule them all: Towards a general deepfake attack detection framework.

LLMs Are Not Yet Ready for Deepfake Image Detection One detector to rule them all: Towards a general deepfake attack detection framework

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.139107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:21.408955Z digest=sha256:379e071ed34be55327c82c170b5381d466794019488f1c11c64620689892aea3

Observation eed62266-385e-4d3e-9d29-7e2830038f21 · outbound

This paper cites Apparatus and method for detecting deepfake based on convolutional long short-term memory network, September 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Apparatus and method for detecting deepfake based on convolutional long short-term memory network, September 2023

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.126579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:21.655476Z digest=sha256:61d9d499b761a35b1a8448ad7458dae99f521bfb611520bb60c3de08b4a2e715

Observation 30188ac1-a1f8-493d-b400-00ded248a167 · outbound

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

LLMs Are Not Yet Ready for Deepfake Image Detection Thinking in frequency: Face forgery detection by mining frequency-aware clues

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:32.024408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:22.316239Z digest=sha256:521c89a026b00ede12ee7e732900af85e55b1bd8ea32e389ace8f5fc35dfae21

Observation 120f3661-76da-4c1d-87ec-9416f6a45bee · outbound

This paper cites Adaptive face forgery detection in cross domain.

LLMs Are Not Yet Ready for Deepfake Image Detection Adaptive face forgery detection in cross domain

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:31.877995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:22.441398Z digest=sha256:0877293ddb0c9947347c06e133271be027a37d8d7d689a5be19466e621c77ac1

Observation 6c16dd89-1d89-4d8c-babc-abc3691eb01c · outbound

This paper cites Add: Frequency attention and multi-view based knowledge distillation to detect low-quality compressed deepfake images.

LLMs Are Not Yet Ready for Deepfake Image Detection Add: Frequency attention and multi-view based knowledge distillation to detect low-quality compressed deepfake images

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:31.637916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:22.578842Z digest=sha256:74ccb25ff89e458b7a773c402669bd7b3f8b6af08ce7c0ce53d3dcd83825e9a4

Observation 6d3a1a97-eadc-47cb-9708-c69deea71135 · outbound

This paper cites Exploring the asynchronous of the frequency spectra of gan-generated facial images.

LLMs Are Not Yet Ready for Deepfake Image Detection Exploring the asynchronous of the frequency spectra of gan-generated facial images

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:31.412605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:22.690066Z digest=sha256:3f733d41c9d1cf2dbbbfe09d6c47e2f89b58295512fe1cec9286c09c48061a15

Observation 89d0a388-eabd-4169-9f69-43ce7ac1f482 · outbound

This paper cites Tar: Generalized forensic framework to detect deepfakes using weakly supervised learning.

LLMs Are Not Yet Ready for Deepfake Image Detection Tar: Generalized forensic framework to detect deepfakes using weakly supervised learning

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:31.273839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:22.850328Z digest=sha256:88c7081e95d55cb3e87c9babbd514ed2015116bf3213e89ac4c76c9efd8d2e8f

Observation 455047e8-5790-4b94-8b58-db7f9522b9be · outbound

This paper cites Detecting hand- crafted facial image manipulations and gan-generated facial images using shallow-fakefacenet.Applied Soft Computing, 105:107256, 2021.

LLMs Are Not Yet Ready for Deepfake Image Detection Detecting hand- crafted facial image manipulations and gan-generated facial images using shallow-fakefacenet.Applied Soft Computing, 105:107256, 2021

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:31.149256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:22.977544Z digest=sha256:095e87edf598b7bfe854a7162ce7279f6bb547d059d94de9ec90c843d72cfd64

Observation f2cebcaf-7547-4794-8ce6-a2e7c1091eb0 · outbound

This paper cites Ugad: Universal generative ai detector utilizing frequency fingerprints.

LLMs Are Not Yet Ready for Deepfake Image Detection Ugad: Universal generative ai detector utilizing frequency fingerprints

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:31.010289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.096862Z digest=sha256:1981381a84c0e6013cedb118395926985a718d3850dd5d715b650815f7800be9

Observation 5bcd3b35-3021-4449-b3a9-d36ccd1ee0bc · outbound

This paper cites Altfreezing for more general video face forgery detection.

LLMs Are Not Yet Ready for Deepfake Image Detection Altfreezing for more general video face forgery detection

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:30.809292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.189555Z digest=sha256:b08d6898d7641e931ea4eab191162a465cb6e9df69b57e7acfb050b7bd998c28

Observation 352a8903-d0e6-47d5-b8e3-7c5f04f5f9e5 · outbound

This paper cites Learning on gradients: Generalized artifacts representation for gan-generated images detection.

LLMs Are Not Yet Ready for Deepfake Image Detection Learning on gradients: Generalized artifacts representation for gan-generated images detection

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:30.626037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.266410Z digest=sha256:418d7fa1784f6ecf8ae0cba3915736c2de8b95b2b24a68c9e8380d95ccec5c6c

Observation c0651b2e-a3cd-4d9a-a827-ddaf6f43c619 · outbound

This paper cites Ptd: Privacy-preserving human face processing framework using tensor decomposition.

LLMs Are Not Yet Ready for Deepfake Image Detection Ptd: Privacy-preserving human face processing framework using tensor decomposition

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:30.502834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.396213Z digest=sha256:a28894f579ae4c04c6c44b7e9fc1f4b6102c06e008b8d86a4cc5a966cca84106

Observation 3ea2fcfd-c1c9-41b1-bf25-890452e986a6 · outbound

This paper cites Cored: Generalizing fake media detection with continual representation using distillation.

LLMs Are Not Yet Ready for Deepfake Image Detection Cored: Generalizing fake media detection with continual representation using distillation

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:30.298403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.498142Z digest=sha256:d731194d97cd511cb4583100940f4b0ee47ad1048f92f643b94a261fb6131101

Observation 2262b015-eaaf-402e-b87f-174f3c292db4 · outbound

This paper cites Fretal: Generalizing deepfake de- tection using knowledge distillation and representation learning.

LLMs Are Not Yet Ready for Deepfake Image Detection Fretal: Generalizing deepfake de- tection using knowledge distillation and representation learning

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:30.139850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.642888Z digest=sha256:f296a0fa831edeb63fd191c131b6ea709247c91e967ecaf4b2be72eee7e5583c

Observation ab79fe96-f26c-4013-964f-45220f9c35b9 · outbound

This paper cites Detecting both machine and human created fake face images in the wild.

LLMs Are Not Yet Ready for Deepfake Image Detection Detecting both machine and human created fake face images in the wild

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:29.993049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.747346Z digest=sha256:ecc849af77e6a5284099c87ca623fba5c11322b6a821ef93f9a70868fdf70a80

Observation 185c6249-ab42-45a1-a447-7390b9102e9f · outbound

This paper cites Gan is a friend or foe?: a framework to detect various fake face images.

LLMs Are Not Yet Ready for Deepfake Image Detection Gan is a friend or foe?: a framework to detect various fake face images

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:29.825231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.801466Z digest=sha256:188c864797b9bfd49b3da6b700b23c8b6984e75f8121ee26c365093c8c146b26

Observation 937b0de3-27b7-4ea1-9f59-2980f829aca6 · outbound

This paper cites A Convolutional LSTM based Residual Network for Deepfake Video Detection.

LLMs Are Not Yet Ready for Deepfake Image Detection A Convolutional LSTM based Residual Network for Deepfake Video Detection

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:23.899685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:23.899685Z digest=sha256:4d129d27433527cad3af0a368275c3b53368027660a543a8aa98fe225f5c64a6

Observation 05ee57fd-aed2-450f-aa98-d752459ec1d4 · outbound

This paper cites Method for performing continual learning using representation learning and apparatus thereof, July.

LLMs Are Not Yet Ready for Deepfake Image Detection Method for performing continual learning using representation learning and apparatus thereof, July

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:29.431032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:23.964521Z digest=sha256:59743406d1743c4c5fec6ba2a9068f278f071eedf6f5b889d7df401413f805c3

Observation d05e214f-5458-46a0-b9ea-8d28932d83a8 · outbound

This paper cites Faceforensics++: Learning to detect manipulated facial images.

LLMs Are Not Yet Ready for Deepfake Image Detection Faceforensics++: Learning to detect manipulated facial images

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:24.147748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:24.147748Z digest=sha256:2583acacb6c25fc518ada166129509302cb0dbea73b3235d9cb6b7c779c1b2d6

Observation 72a4a22a-00fb-4a4e-bc0e-ce5525201662 · outbound

This paper cites The DeepFake Detection Challenge (DFDC) Dataset.

LLMs Are Not Yet Ready for Deepfake Image Detection The DeepFake Detection Challenge (DFDC) Dataset

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:24.210000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:24.210000Z digest=sha256:c87c1dcfe6b42ae1c366ba39a7b8ce7f4603a303951e1524d7c5a1fb3441f5ec

Observation 465d4b17-9d24-4ac4-8ece-69e43e8cb129 · outbound

This paper cites Evaluation of an audio-video multimodal deepfake dataset using unimodal and multimodal detectors.

LLMs Are Not Yet Ready for Deepfake Image Detection Evaluation of an audio-video multimodal deepfake dataset using unimodal and multimodal detectors

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:28.920795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.296483Z digest=sha256:83df78720060b38cfa0d110c838ff7f6c4dee4821f48f64939bd28a064f4ab36

Observation 26909760-4568-4a87-b21b-162a580ecf0b · outbound

This paper cites Fakeavceleb: A novel audio-video multimodal deepfake dataset.

LLMs Are Not Yet Ready for Deepfake Image Detection Fakeavceleb: A novel audio-video multimodal deepfake dataset

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:28.622741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.380918Z digest=sha256:1e1eaa173b79fe31d7554826086ce747472a2976030359bb913f0f23307521d6

Observation 4da538ac-bdc2-4cbc-a995-0a90f3543938 · outbound

This paper cites Celeb-df: A large- scale challenging dataset for deepfake forensics.

LLMs Are Not Yet Ready for Deepfake Image Detection Celeb-df: A large- scale challenging dataset for deepfake forensics

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:28.412595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.470924Z digest=sha256:be543cd5cdbbcb108dd6921f05caf021e2c62eb0f45891e51c05b4006a6dedfd

Observation ed46d027-4df9-44a6-be8c-23ef60c0c390 · outbound

This paper cites Le, Jiwon Kim, Simon S.

LLMs Are Not Yet Ready for Deepfake Image Detection Le, Jiwon Kim, Simon S

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:28.145136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.569242Z digest=sha256:58274bc226bbbab251bf42650e5f2d2d34e01f07e0633b190ad83e8b30cb7252

Observation f945e729-d658-4fea-be2c-4c206bf6422b · outbound

This paper cites Towards understanding of deepfake videos in the wild.

LLMs Are Not Yet Ready for Deepfake Image Detection Towards understanding of deepfake videos in the wild

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:27.907961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.635339Z digest=sha256:9ef38d1dea7b158144f0eb61b8f0ebfd94ae3b73183c5479274653065d55e3af

Observation 0fb313cb-9b3d-4724-9908-91d664e7c9aa · outbound

This paper cites Why do facial deepfake detectors fail? InProceedings of the 2nd Workshop on Security Implications of Deepfakes and Cheapfakes, WDC ’23, page 24–28, New York, NY, USA, 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Why do facial deepfake detectors fail? InProceedings of the 2nd Workshop on Security Implications of Deepfakes and Cheapfakes, WDC ’23, page 24–28, New York, NY, USA, 2023

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:27.680313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.676474Z digest=sha256:4a150910a22a94041f9802313e6298445791680322760984c0fec221f0d2bff3

Observation 82867562-d023-495b-9f28-424397efa800 · outbound

This paper cites Woo, and Shahroz Tariq.

LLMs Are Not Yet Ready for Deepfake Image Detection Woo, and Shahroz Tariq

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:27.470911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.727864Z digest=sha256:e4a8f99b4187ec40ebe164e5c9656ec1e63f04e38889a869168696b1bfb9832b

Observation ef39bb8f-a110-4869-b1a4-05c5d0b1c88c · outbound

This paper cites Woo, and Shahroz Tariq.

LLMs Are Not Yet Ready for Deepfake Image Detection Woo, and Shahroz Tariq

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:27.327116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.818235Z digest=sha256:85313f28fe3a42374cefef8f4358f191c594c9c4d41b9003e886d6e5be96a3b4

Observation 241d6679-3c86-4ba8-b557-66bbba1cf868 · outbound

This paper cites Chatgpt: A conversational ai model, 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Chatgpt: A conversational ai model, 2023

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:27.216342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.881367Z digest=sha256:cc408d26dd8438c8f08ee96dd454a1714b42e4e87e684dd3611483d63b29f753

Observation 06405d73-178b-4129-8d68-8f0643b34c74 · outbound

This paper cites Gemini: Multimodal ai by google deepmind, 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Gemini: Multimodal ai by google deepmind, 2023

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:27.083506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.974459Z digest=sha256:2d638eb09196614935b6e48003f027a2d781bd0bcf5cb778d1b26a039cac1e06

Observation 23fcc478-07f6-45f3-bdea-312e4c7cf65e · outbound

This paper cites Claude: Constitutional ai assistant, 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Claude: Constitutional ai assistant, 2023

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:26.972745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.039281Z digest=sha256:d29bc45f69b4d0f75cf388bab5e419e90bd2745636b06bc2b8085a37cc97284c

Observation 71a3ebd9-615d-4566-ac00-1139f206b6bf · outbound

This paper cites Grok: Conversational ai by xai, 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Grok: Conversational ai by xai, 2023

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:26.896634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.115934Z digest=sha256:2201b70173538a4ad3143120c7e64c548a50356518669ffe72824ac685091cc8

Observation 3753b36c-73a0-4fb8-a874-ac8135401ad5 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.Advances in neural Shahroz Tariq, David Nguyen, M.A.P.

LLMs Are Not Yet Ready for Deepfake Image Detection Flamingo: a visual language model for few-shot learning.Advances in neural Shahroz Tariq, David Nguyen, M.A.P

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:26.777699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.179548Z digest=sha256:b1a615aceee29d612e7c4fa7d4f04fc31a8f618ab2687c5aa2fde7006ee764d5

Observation 2ee725cf-5702-49d7-a76b-b122c51ba9a3 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

LLMs Are Not Yet Ready for Deepfake Image Detection Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:25.232560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:25.232560Z digest=sha256:41e38c1d11c19021285a6489c733810f85ee0fb8468c5e08e36ab13374115c67

Observation 63e0b501-9567-4f46-bc13-e69e816f1a32 · outbound

This paper cites AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors.

LLMs Are Not Yet Ready for Deepfake Image Detection AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:25.312097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:25.312097Z digest=sha256:dcf685c131bff7a5fb49aee91facf8d311d4c2df849d6b95bc45b5effcaa0586

Observation 1e60114e-a256-4e15-9965-efbdf65fe021 · outbound

This paper cites Can chatgpt detect deepfakes? a study of using multimodal large language models for media forensics.

LLMs Are Not Yet Ready for Deepfake Image Detection Can chatgpt detect deepfakes? a study of using multimodal large language models for media forensics

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:26.662824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.377770Z digest=sha256:58a7c0b3873281f98c84b00570a825542c45242dffe93782f358c26b3e89cc4d

Observation 87576051-c288-4d70-8e51-c4ca8453a50e · outbound

This paper cites Can Multi-modal (reasoning) LLMs work as deepfake detectors?.

LLMs Are Not Yet Ready for Deepfake Image Detection Can Multi-modal (reasoning) LLMs work as deepfake detectors?

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:25.415369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:25.415369Z digest=sha256:0d401bc3b0c61720fc1f901b3d30c6eac5b434a0841981d5a9498897728186bd

Observation 21eb88c4-2b75-4dd9-80b7-dc33433f6025 · outbound

This paper cites The gan is dead; long live the gan! a modern gan baseline.Advances in Neural Information Processing Systems, 37:44177–44215, 2024.

LLMs Are Not Yet Ready for Deepfake Image Detection The gan is dead; long live the gan! a modern gan baseline.Advances in Neural Information Processing Systems, 37:44177–44215, 2024

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:26.562695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.465268Z digest=sha256:0b66b07b39e0c6513536cf1b7b4fd6c5605bc7b2b37c31accf02b8fa873abe45

Observation 0af91e14-d6c3-4c1f-8447-670f13d22d1e · outbound

This paper cites A2c: A modular multi-stage collaborative decision framework for human–ai teams.

LLMs Are Not Yet Ready for Deepfake Image Detection A2c: A modular multi-stage collaborative decision framework for human–ai teams

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:26.458253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.532533Z digest=sha256:faef8b8a262230de673375da7172a597502582880fe7e62502d3285bb7bd4304

Observation 4003423e-03b9-4ec8-b6f0-2432bdf7f540 · outbound

This paper cites Towards a criteria-based approach to selecting human-AI interaction mode.

LLMs Are Not Yet Ready for Deepfake Image Detection Towards a criteria-based approach to selecting human-AI interaction mode

Reference 52

Resolution
verified exact
local_arxiv, observed 2026-08-07T04:32:26.092349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.633017Z digest=sha256:ce954d8a66033f2160875e0a061d3649091381e2126a481adb9266ee9366a477

Observation 780956cd-3470-4b3a-a16d-c08f05dd6597 · outbound

This paper cites Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for Cybersecurity.

LLMs Are Not Yet Ready for Deepfake Image Detection Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for Cybersecurity

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:25.700574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:25.700574Z digest=sha256:fd7ff4ab5a96a69fe111e55eeb8e50c7cb28c6d104fc4a3b37e8ef23bda6c594

Observation 568e76db-a616-4cf8-942c-ac94db4ad52e · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

LLMs Are Not Yet Ready for Deepfake Image Detection Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-07T04:32:25.805203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:32:25.805203Z digest=sha256:358822045a0da763e33f1483f3ef24fa0b7560f1bd41abc67cd63f97927f9803

Observation d0df8c5f-d00f-4346-b9ce-b6cdeb6f8452 · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large lan- guage models.

LLMs Are Not Yet Ready for Deepfake Image Detection Minigpt-4: Enhancing vision-language understanding with advanced large lan- guage models

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:26.307347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:25.888929Z digest=sha256:41e6a4561a773b30838d7b720e20557972d3e74583a5a3b3dbb0b51487d4ae81

Observation 0b485d12-0077-4209-b112-451a3fa2ceeb · outbound

This paper cites 18/092,590.

LLMs Are Not Yet Ready for Deepfake Image Detection 18/092,590

Reference 2023

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:32:29.197750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-07T04:32:24.056104Z digest=sha256:b25d827dcad963e87df172b6dfff9c612055cf384d695e93e5f0587b1701216e

Pith citing papers

Observation a0bc6f27-2b13-41cd-963e-c9a9b79b107c · inbound

The Age of Sensorial Zero Trust: Why We Can No Longer Trust Our Senses cites this paper.

The Age of Sensorial Zero Trust: Why We Can No Longer Trust Our Senses LLMs Are Not Yet Ready for Deepfake Image Detection

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T21:08:54.359370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:08:54.359370Z digest=sha256:063f427344948e74c735b035e9df5d974c4945c2bc10ed7532f949d3616ea66b

Observation fe2e8c30-7841-40ba-802c-261fa120293d · inbound

On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations cites this paper.

On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations LLMs Are Not Yet Ready for Deepfake Image Detection

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-06T11:48:58.556863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T11:48:58.556863Z digest=sha256:880de3074b9e35b159e00cc6b491b14d53205c24b580ebb2dee3fc706355595e

Observation 749ea955-b750-4e6a-8442-357fc33e1914 · inbound

From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users cites this paper.

From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users LLMs Are Not Yet Ready for Deepfake Image Detection

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-05T22:03:46.345751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T22:03:46.345751Z digest=sha256:14cb35cfeddb514aed940b43382d2d8a19a8bd7fa51684b8dbf3eccecdcb0c6b

Observation 9279e007-d57b-4c55-8dc9-e0f9c5451c40 · inbound

Trustworthy Image Authentication using Forensic Knowledge Graphs cites this paper.

Trustworthy Image Authentication using Forensic Knowledge Graphs LLMs Are Not Yet Ready for Deepfake Image Detection

Reference 79

Resolution
verified exact
arxiv_id, observed 2026-07-04T10:39:45.173347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-06-26T08:39:35.247055Z digest=sha256:3139096a120649fc80e204dbcba822b6d234b742a5157060689e36e965184a2c