Lights, Camera, Attack: Exploiting Temporal HDR Fusion with Pulsed Light

2026-09-29

AI Summary

Temporal HDR fusion relies on the assumption of illumination stability, rendering it susceptible to physical-layer interference. This work proposes FLASH, an adversarial attack that exploits external pulsed light to induce cross-exposure frame inconsistencies, thereby violating this fundamental algorithmic assumption. Notably, FLASH achieves platform-agnostic perceptual disruption without requiring hardware access, phase locking, or raw data acquisition. Experimental evaluations demonstrate that FLASH induces extreme darkening rates of up to 50% on devices such as iPhones, significantly degrading target contrast and triggering low-visibility alerts. Furthermore, physical-world testing in OpenPilot autonomous driving scenarios validates both the practical efficacy of the proposed attack and the feasibility of potential defense mechanisms.

Abstract

Modern cameras widely use temporal High Dynamic Range (HDR) to improve visibility by capturing a sequence of exposures with different integration times and fusing them into a single image. This process implicitly assumes that scene illumination remains sufficiently stable during capture. We introduce FLASH (Fusion-Level Attack by Saturating HDR), an external pulsed-light attack that deliberately attacks this assumption by creating cross-exposure inconsistency before downstream perception. FLASH exploits an algorithmic assumption rather than relying on sensor damage or hardware failure, and requires neither physical camera access, access to raw exposure brackets, knowledge of the fusion algorithm, nor exact phase lock to the camera. Across eight physical camera platforms spanning embedded, surveillance, photography, smartphone, and automotive use cases, and matched optical controls, FLASH causes pipeline-dependent darkening, overexposure, and visibility loss. This includes extreme-darkening rates of 50.0% on an iPhone 16 Pro and 33.7% on a Wyze Battery Cam Pro. On the Wyze camera, FLASH triggers the system-level low-visibility response in 10/10 trials, compared with 0/10 continuous-light and randomized-frequency flashing controls. In a controlled stationary OpenPilot case study, 23.0% of frames exhibit severe darkening in the traffic-cone target region, with target-background CNR decreasing by up to 90.8%. Under FLASH, the OpenPilot interface also fails to display the system-level path state observed in the corresponding control trials. In a controlled night-only HDR reconstruction stress test, a proof-of-concept exposure-rejection defense reduces median output-brightness deviation by 79.16%. These results show that temporal HDR fusion itself requires security-aware validation of exposure evidence.

Problem

• Temporal HDR Fusion
• Pulsed Light Attack
• Camera Security
• Adversarial Attack
• Autonomous Driving

Innovation

• Temporal HDR Fusion
• Pulsed Light Attack
• Adversarial Attack
• Autonomous Driving Security
• Exposure Rejection Defense