Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object Detection

TL;DR

This paper introduces {}-Cloak, a novel no-box adversarial attack on video object detection that exploits the alpha channel to create visually stealthy yet highly effective attacks, exposing a new vulnerability in video perception systems.

Contribution

It presents the first alpha channel-based no-box attack on video object detectors, demonstrating its effectiveness and revealing a new security vulnerability.

Findings

Achieved 100% attack success rate across multiple detectors.

Exposed alpha channel as a previously overlooked attack surface.

Demonstrated the attack's stealthiness and broad applicability.

Abstract

As object detection models are increasingly deployed in cyber-physical systems such as autonomous vehicles (AVs) and surveillance platforms, ensuring their security against adversarial threats is essential. While prior work has explored adversarial attacks in the image domain, those attacks in the video domain remain largely unexamined, especially in the no-box setting. In this paper, we present {\alpha}-Cloak, the first no-box adversarial attack on object detectors that operates entirely through the alpha channel of RGBA videos. {\alpha}-Cloak exploits the alpha channel to fuse a malicious target video with a benign video, resulting in a fused video that appears innocuous to human viewers but consistently fools object detectors. Our attack requires no access to model architecture, parameters, or outputs, and introduces no perceptible artifacts. We systematically study the support for alpha channels across common video formats and playback applications, and design a fusion algorithm that ensures visual stealth and compatibility. We evaluate {\alpha}-Cloak on five state-of-the-art object detectors, a vision-language model, and a multi-modal large language model (Gemini-2.0-Flash), demonstrating a 100% attack success rate across all scenarios. Our findings reveal a previously unexplored vulnerability in video-based perception systems, highlighting the urgent need for defenses that account for the alpha channel in adversarial settings.