发表机构
Lomonosov Moscow State University; MSU Institute for Artificial Intelligence（莫斯科国立罗蒙诺索夫大学; 莫斯科国立大学人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
VCR-Bench是一个模块化开源基准框架，标准化视频分类鲁棒性评估，整合30个模型、14种攻击和10种防御，在Kinetics-400上报告多维度指标。
AI 中文摘要
图像分类的鲁棒性已有多个基准，但视频领域的对应基准尚属空白。在视频分类中，时间维度为对抗攻击、防御和预处理引入了额外的自由度。时间采样、扰动预算和度量聚合的交互方式在图像设定中没有直接对应物。因此，视频分类器的鲁棒性研究分散在不兼容的实现中，导致报告的数字难以复现和分析。我们推出了VCR-Bench，一个模块化的开源基准框架，它标准化了视频加载、分类器封装、对抗攻击与防御、感知度量、配置预设和结果记录。VCR-Bench目前整合了30个视频分类模型、14种对抗攻击和10种防御封装，在统一的评估协议下运行。我们在Kinetics-400子集上评估了代表性的视频分类器、攻击和防御，报告了干净准确率、攻击成功率、感知质量、运行时间和内存使用。VCR-Bench已发布，附带文档化的安装说明、可复现的运行预设、组件扩展接口以及用于复现报告结果的脚本，可在该https URL获取。
英文摘要
Robustness of image classification has several benchmarks, but their video counterparts are absent. In video classification temporal dimension introduces additional degrees of freedom for adversarial attacks, defenses, and preprocessing. Temporal sampling, perturbation budgets, and metric aggregation also interact in ways with no direct analogue in the image setting. Therefore, robustness for video classifiers is studied across scattered, incompatible implementations, making reported numbers hard to reproduce and analyze. We introduce VCR-Bench, a modular open-source benchmark framework that standardizes video loading, wrappers for classifiers, adversarial attacks and defenses, perceptual metrics, configuration presets, and result logging. VCR-Bench currently integrates 30 video classification models, 14 adversarial attacks, and 10 defense wrappers under a common evaluation protocol. We evaluate representative video classifiers, attacks, and defenses on Kinetics-400 subset, reporting clean accuracy, attack success rate, perceptual quality, runtime, and memory usage. VCR-Bench is released with documented installation, reproducible run presets, component-extension interfaces, and scripts for reproducing the reported results at https://github.com/msu-video-group/vcr-bench.
Comments6 pages,1 figure, accepted at ACM MM 2026
