Physically Realistic Sequence-Level Adversarial Clothing for Robust Human-Detection Evasion

TL;DR

This paper introduces a sequence-level optimization method to generate adversarial clothing textures that effectively evade human detection across entire videos, maintaining concealment despite motion, pose changes, and environmental variations.

Contribution

It presents a novel sequence-level adversarial texture generation framework that ensures long-term concealment in real-world scenarios, surpassing prior frame-by-frame approaches.

Findings

Effective concealment across entire video sequences

High robustness to viewpoint and environmental changes

Physical garments successfully evade detection in real-world tests

Abstract

Deep neural networks used for human detection are highly vulnerable to adversarial manipulation, creating safety and privacy risks in real surveillance environments. Wearable attacks offer a realistic threat model, yet existing approaches usually optimize textures frame by frame and therefore fail to maintain concealment across long video sequences with motion, pose changes, and garment deformation. In this work, a sequence-level optimization framework is introduced to generate natural, printable adversarial textures for shirts, trousers, and hats that remain effective throughout entire walking videos in both digital and physical settings. Product images are first mapped to UV space and converted into a compact palette and control-point parameterization, with ICC locking to keep all colors printable. A physically based human-garment pipeline is then employed to simulate motion, multi-angle camera viewpoints, cloth dynamics, and illumination variation. An expectation-over-transformation objective with temporal weighting is used to optimize the control points so that detection confidence is minimized across whole sequences. Extensive experiments demonstrate strong and stable concealment, high robustness to viewpoint changes, and superior cross-model transferability. Physical garments produced with sublimation printing achieve reliable suppression under indoor and outdoor recordings, confirming real-world feasibility.