Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2411.03554 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913724121481216 |
|---|---|
| author | Ma, Yingzi Wang, Jiongxiao Wang, Fei Ma, Siyuan Li, Jiazhao Pan, Jinsheng Li, Xiujun Huang, Furong Sun, Lichao Li, Bo Choi, Yejin Chen, Muhao Xiao, Chaowei |
| author_facet | Ma, Yingzi Wang, Jiongxiao Wang, Fei Ma, Siyuan Li, Jiazhao Pan, Jinsheng Li, Xiujun Huang, Furong Sun, Lichao Li, Bo Choi, Yejin Chen, Muhao Xiao, Chaowei |
| contents | Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy concerns in Vision Language Models (VLMs) remain underexplored. To address this, we introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms under the Right to be Forgotten setting. Specifically, we formulate the VLM unlearning task via constructing the Fictitious Facial Identity VQA dataset and apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels. In terms of evaluation, since VLM supports various forms of ways to ask questions with the same semantic meaning, we also provide robust evaluation metrics including membership inference attacks and carefully designed adversarial privacy attacks to evaluate the performance of algorithms. Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance, with significant trade-offs between model utility and forget quality. Furthermore, our findings also highlight the importance of privacy attacks for robust evaluations. We hope FIUBench will drive progress in developing more effective VLM unlearning algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03554 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset Ma, Yingzi Wang, Jiongxiao Wang, Fei Ma, Siyuan Li, Jiazhao Pan, Jinsheng Li, Xiujun Huang, Furong Sun, Lichao Li, Bo Choi, Yejin Chen, Muhao Xiao, Chaowei Computer Vision and Pattern Recognition Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy concerns in Vision Language Models (VLMs) remain underexplored. To address this, we introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms under the Right to be Forgotten setting. Specifically, we formulate the VLM unlearning task via constructing the Fictitious Facial Identity VQA dataset and apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels. In terms of evaluation, since VLM supports various forms of ways to ask questions with the same semantic meaning, we also provide robust evaluation metrics including membership inference attacks and carefully designed adversarial privacy attacks to evaluate the performance of algorithms. Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance, with significant trade-offs between model utility and forget quality. Furthermore, our findings also highlight the importance of privacy attacks for robust evaluations. We hope FIUBench will drive progress in developing more effective VLM unlearning algorithms. |
| title | Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.03554 |