Parameter-matched LoRA placement reveals performance–efficiency trade-offs in cross-dataset deepfake detection

Cross-dataset generalization remains difficult in deepfake detection, and the placement of parameter-efficient adaptation within pretrained vision models remains insufficiently controlled. We study standard weight-space Low-Rank Adaptation (LoRA) in CLIP ViT-L/14 from two complementary perspectives. A primary comparison evaluated attention output (Attn-Out), attention query/value (Attn-Q/V), MLP, and MLP+Attn-Out using exactly 1,478,658 trainable parameters each and three independent seeds. A common-rank contrast showed that Attn-Out used 49.9% fewer trainable parameters than Attn-Q/V at \(r=16\) , while its source-validation frame-level AUC was lower by 0.000659. Models were trained on FaceForensics++ C23, and configurations were frozen using source validation before evaluation on six reporting-only external datasets. In the exact-budget comparison, Attn-Q/V achieved the highest observed mean Macro-6 AUC ( \(0.9432\,\pm\,0.0010\) ), whereas Attn-Out led numerically on three targets and required less measured training memory and model-compute time. All family-balanced crossed-bootstrap intervals included zero, so the AUC ordering is descriptive. Explicit merging removed placement-specific low-rank operations, and inference measurements did not support a deployment-speed ranking. Together, these comparisons separate adapter size and training-resource requirements from merged inference behavior.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-19
DOI
https://doi.org/10.1038/s41598-026-80070-7
Primary Topic
Digital Media Forensic Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Parameter-matched LoRA placement reveals performance–efficiency trade-offs in cross-dataset deepfake detection

Hyunsoo Kang, Dohyeon Kim
Scientific Reports
Digital Media Forensic Detection
article

Parameter-matched LoRA placement reveals performance–efficiency trade-offs in cross-dataset deepfake detection

Hyunsoo Kang, Dohyeon Kim
article en

Abstract

Cross-dataset generalization remains difficult in deepfake detection, and the placement of parameter-efficient adaptation within pretrained vision models remains insufficiently controlled. We study standard weight-space Low-Rank Adaptation (LoRA) in CLIP ViT-L/14 from two complementary perspectives. A primary comparison evaluated attention output (Attn-Out), attention query/value (Attn-Q/V), MLP, and MLP+Attn-Out using exactly 1,478,658 trainable parameters each and three independent seeds. A common-rank contrast showed that Attn-Out used 49.9% fewer trainable parameters than Attn-Q/V at \(r=16\) , while its source-validation frame-level AUC was lower by 0.000659. Models were trained on FaceForensics++ C23, and configurations were frozen using source validation before evaluation on six reporting-only external datasets. In the exact-budget comparison, Attn-Q/V achieved the highest observed mean Macro-6 AUC ( \(0.9432\,\pm\,0.0010\) ), whereas Attn-Out led numerically on three targets and required less measured training memory and model-compute time. All family-balanced crossed-bootstrap intervals included zero, so the AUC ordering is descriptive. Explicit merging removed placement-specific low-rank operations, and inference measurements did not support a deployment-speed ranking. Together, these comparisons separate adapter size and training-resource requirements from merged inference behavior.

Scientific Reports
Chungbuk National University (KR)
Digital Media Forensic Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon