VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. Despite their widespread use, these paradigms are rarely evaluated under a common protocol, making direct comparison difficult. We introduce VendorBench-100, a cross-paradigm benchmark that evaluates 36 representative models using a single adversarial 100-image corpus, a unified output schema, and a common evaluation framework. To ensure reliable assessment under the corpus's intentional class imbalance, models are ranked
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorSharayu N. Deshmukh →
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
- Linked via arxiv authorMd Rashidunnabi →
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
- Linked via arxiv authorNelton Tiago Gemo →
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
- Linked via arxiv authorKurundkar G. D. →
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
- Linked via arxiv authorMahamune M. R. →
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
- Linked via arxiv authorNilesh K. Deshmukh →
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection