Machine unlearning (MU) refers to the post-training capability to remove (the influence of) training examples that are incorrect, biased, or leak sensitive/private information. MU is now widely regarded as critical for building safe and fair AI. In parallel, research into transformer architectures for computer vision has been highly successful: Vision Transformers (VTs) increasingly emerge as strong alternatives to CNNs. Yet, MU research for vision tasks has largely centered on CNNs, not VTs. While MU benchmarks have been developed for LLMs, diffusion models, and CNNs, none currently exist for VTs. This work is the first to attempt this, benchmarking MU algorithm performance across different VT families (ViT, Swin-T, and DINOv2) and at different capacities. The work employs (i) different datasets, selected to assess the impacts of dataset scale and complexity; (ii) different MU algorithms, selected to represent fundamentally different approaches for MU; and (iii) both single-shot and continual unlearning protocols. Additionally, it focuses on benchmarking MU algorithms that leverage training data memorization, since leveraging memorization has been recently discovered to significantly improve the performance of previously SOTA algorithms. En route, the work characterizes how VTs memorize training data relative to CNNs, and assesses the impact of different memorization proxies on performance. The benchmark uses unified evaluation metrics that capture two complementary notions of forget quality along with accuracy on unseen (test) data and on retained data. Overall, this work offers a benchmarking basis, enabling reproducible, fair, and comprehensive comparisons of existing (and future) MU algorithms on VTs. Importantly, for the first time, it sheds light on how well existing algorithms work in VT settings, establishing a promising reference performance baseline.
Rethinking Machine Unlearning in Image Generation Models
Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；School of Artificial Intelligence and Data Science, University of Science and Technology of China（中国科学技术大学人工智能与数据科学学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；National Pilot School of Software, Yunnan University（云南大学软件试点学院）；AI Safety of Chinese Academy of Sciences, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院人工智能安全研究院、计算技术研究所）
Vision Transformers for Zero-Shot Clustering of Animal Images: A Comparative Benchmarking Study
Department of Chemistry and Bioscience（化学与生物科学系）；Aalborg University（奥尔堡大学）；Department of Architecture, Design and Media Technology（建筑、设计与媒体技术系）；Visual Analysis and Perception Lab（视觉分析与感知实验室）
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；USC（南加州大学）；University of Michigan-Ann Arbor（密歇根大学安娜堡分校）；University of Washington（华盛顿大学）；University of Maryland（马里兰大学）；Lehigh University（理海大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Peking University（北京大学）；University of Rochester（罗切斯特大学）；University of California, Davis（加州大学戴维斯分校）
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques
State Key Lab of Software Development Environment, Beihang University（北京航空航天大学软件开发环境国家重点实验室）；SenseTime（商汤科技）；Berkeley Artificial Intelligence Research Lab, University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Oxford（牛津大学）；JD Explore Academy（京东探索研究院）
Benchmarking Edge Inference Strategies for Deep Learning Models in Industrial Machine Vision
Spanish Ministry of Science, Innovation and Universities（西班牙科学、创新与大学部）；Spanish State Research Agency（西班牙国家研究机构）；European Regional Development Fund（欧洲区域发展基金）；European Union（欧洲联盟）；European Health and Digital Executive Agency（欧洲健康与数字执行机构）
Benchmarking Advanced Text Anonymisation Methods: A Comparative Study on Novel and Traditional Approaches
MetaMind Innovations P.C.（MetaMind创新股份有限公司）；University of Western Macedonia（西马其顿大学）；Kingston University（金斯顿大学）；Sidroco Holdings Ltd.（Sidroco控股有限公司）；Aristotle University of Thessaloniki（亚里士多德大学）；University of Peloponnese（伯罗奔尼撒大学）；University of Macedonia（马其顿大学）
Benchmarking Artificial Intelligence Models for Daily Coastal Hypoxia Forecasting
Department of Environmental Sciences, Louisiana State University（环境科学系，路易斯安那州立大学）；Center for Computation and Technology, Louisiana State University（计算与技术中心，路易斯安那州立大学）；Department of Computer Science, Louisiana State University（计算机科学系，路易斯安那州立大学）；Department of Computer Science, Furman University（计算机科学系，富兰克林大学）；Department of Oceanography and Coastal Sciences, Louisiana State University（海洋学与沿海科学系，路易斯安那州立大学）
OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records
The First Affiliated Hospital, Jiangxi Medical College, Nanchang University（南昌大学江西医学院第一附属医院）；Nanchang University（南昌大学）；Georgia Institution of Technology（佐治亚理工学院）
Delta-Influence: Unlearning Poisons via Influence Functions
ShanghaiTech University（上海科技大学）；Tsinghua University（清华大学）；University of Oxford（牛津大学）；Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学）；University of Copenhagen（哥本哈根大学）
Open-Source Manually Annotated Vocal Tract Database for Automatic Segmentation from 3D MRI Using Deep Learning: Benchmarking 2D and 3D Convolutional and Transformer Networks
University of Iowa（爱荷华大学）；Shenandoah University（谢南多厄大学）
