Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912288945995776 |
|---|---|
| author | Wang, Jin Lv, Chenghui Li, Xian Dong, Shichao Li, Huadong Yao, kelu Li, Chao Shao, Wenqi Luo, Ping |
| author_facet | Wang, Jin Lv, Chenghui Li, Xian Dong, Shichao Li, Huadong Yao, kelu Li, Chao Shao, Wenqi Luo, Ping |
| contents | Recently, the rapid development of AIGC has significantly boosted the diversities of fake media spread in the Internet, posing unprecedented threats to social security, politics, law, and etc. To detect the ever-increasingly diverse malicious fake media in the new era of AIGC, recent studies have proposed to exploit Large Vision Language Models (LVLMs) to design robust forgery detectors due to their impressive performance on a wide range of multimodal tasks. However, it still lacks a comprehensive benchmark designed to comprehensively assess LVLMs' discerning capabilities on forgery media. To fill this gap, we present Forensics-Bench, a new forgery detection evaluation benchmark suite to assess LVLMs across massive forgery detection tasks, requiring comprehensive recognition, location and reasoning capabilities on diverse forgeries. Forensics-Bench comprises 63,292 meticulously curated multi-choice visual questions, covering 112 unique forgery detection types from 5 perspectives: forgery semantics, forgery modalities, forgery tasks, forgery types and forgery models. We conduct thorough evaluations on 22 open-sourced LVLMs and 3 proprietary models GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet, highlighting the significant challenges of comprehensive forgery detection posed by Forensics-Bench. We anticipate that Forensics-Bench will motivate the community to advance the frontier of LVLMs, striving for all-around forgery detectors in the era of AIGC. The deliverables will be updated at https://Forensics-Bench.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15024 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models Wang, Jin Lv, Chenghui Li, Xian Dong, Shichao Li, Huadong Yao, kelu Li, Chao Shao, Wenqi Luo, Ping Computer Vision and Pattern Recognition Recently, the rapid development of AIGC has significantly boosted the diversities of fake media spread in the Internet, posing unprecedented threats to social security, politics, law, and etc. To detect the ever-increasingly diverse malicious fake media in the new era of AIGC, recent studies have proposed to exploit Large Vision Language Models (LVLMs) to design robust forgery detectors due to their impressive performance on a wide range of multimodal tasks. However, it still lacks a comprehensive benchmark designed to comprehensively assess LVLMs' discerning capabilities on forgery media. To fill this gap, we present Forensics-Bench, a new forgery detection evaluation benchmark suite to assess LVLMs across massive forgery detection tasks, requiring comprehensive recognition, location and reasoning capabilities on diverse forgeries. Forensics-Bench comprises 63,292 meticulously curated multi-choice visual questions, covering 112 unique forgery detection types from 5 perspectives: forgery semantics, forgery modalities, forgery tasks, forgery types and forgery models. We conduct thorough evaluations on 22 open-sourced LVLMs and 3 proprietary models GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet, highlighting the significant challenges of comprehensive forgery detection posed by Forensics-Bench. We anticipate that Forensics-Bench will motivate the community to advance the frontier of LVLMs, striving for all-around forgery detectors in the era of AIGC. The deliverables will be updated at https://Forensics-Bench.github.io/. |
| title | Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15024 |