Unverified50% confidenceFactExact time
IAU-FOA is a transferable adversarial attack method that combines visual invariance augmentation and feature optimal alignment, simultaneously aligning adversarial examples and target samples at both global and local levels.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedARKit底层依赖视觉惯性里程计（VIO）技术，融合摄像头视觉特征点追踪与IMU惯性传感器数据实现空间锚定64% similarUnverifiedExisting mainstream targeted transfer attacks primarily rely on global image-level features for alignment, such as the [CLS] embedding vector of the encoder.64% similarUnverifiedThe enemy AI in Mankind Divided operates on a multi-layer perception model, where the vision cone dynamically adjusts detection probability based on lighting intensity and distance, and the auditory system calculates footstep sound propagation range based on floor material.62% similarUnverifiedARKit的底层依赖Visual-Inertial Odometry（视觉惯性里程计）技术，将视觉特征点追踪与IMU惯性传感器数据融合61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983379API
curl https://kongchang.com/api/v1/knowledge/claims/983379MCP
get_claim(id=983379)