ALLUDE：可微环境中可配置攻击的统一评估系统
ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
浏览论文内容
中文总结 AI 辅助
针对视觉模型对抗攻击评估条件有限的问题，ALLUDE提供统一评估系统，通过拉丁超立方抽样和压力测试现有攻击展示评估广度，利用端到端可微渲染针对实际部署优化攻击，且跨平台代码开源。
中文摘要 AI 辅助
对目标检测器等视觉模型的对抗攻击评估条件有限，性能未充分表征。整合模拟和可微渲染能实现更强大的端到端评估，但缺乏易用统一系统。ALLUDE填补了这些空白，通过双管齐下策略展示评估广度：一是拉丁超立方抽样，二是压力测试现有攻击。其端到端可微渲染能针对实际部署条件优化攻击，跨平台代码开源。
英文摘要
Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and differentiable rendering enables more robust, end-to-end evaluation of these adversarial attacks, yet there is no easy-to-use, unified system that offers a rich set of customizable configurations for adversarial attacks across multiple scenes, objects, environmental and lighting conditions, and camera trajectories. We present ALLUDE, which addresses these gaps, offering first-of-its-kind evaluation capabilities across Linux and Windows. We comprehensively demonstrate ALLUDE's evaluation breadth through a two-pronged strategy: (1) using Latin Hypercube Sampling, we draw a representative subset from 5,400 configurations spanning 10 scene-object pairs, 9 weather conditions, 4 optimizers, 5 camera trajectories, and 3 detection models; (2) we stress-test existing attacks (CAMOU, RAUCA, FCA) under diverse weather conditions and continuous camera trajectories, revealing degradation of attack success across every attack, exposing evaluation gaps in prior work. Through ALLUDE's end-to-end differentiable rendering, adversarial attacks can be optimized against shifting real-world deployment conditions. Our cross-platform code is open source.
发表机构
- Georgia Institute of Technology（佐治亚理工学院）
- Technological Innovation Institute（技术创新研究所）
机构由 AI 辅助整理，请以论文原文为准。
