Lights, Camera, Attack: Exploiting Temporal HDR Fusion with Pulsed Light
Pulsed-light FLASH attack disrupts temporal HDR fusion, darkening iPhone, Wyze, and OpenPilot camera pipelines.
The paper introduces FLASH, an external pulsed-light attack that creates cross-exposure inconsistency in temporal HDR fusion without damaging the sensor or requiring camera access. Across eight physical platforms, it caused pipeline-dependent darkening, overexposure, and visibility loss, including 50.0% extreme darkening on an iPhone 16 Pro and 33.7% on a Wyze Battery Cam Pro. On Wyze, FLASH triggered the low-visibility response in 10 of 10 trials versus 0 of 10 for continuous-light and randomized-flash controls. In a stationary OpenPilot case, 23.0% of frames showed severe darkening in the traffic-cone region and target-background CNR fell by up to 90.8%; a night-only exposure-rejection defense reduced median brightness deviation by 79.16%.
- FLASH needs no camera access, raw brackets, or fusion-algorithm knowledge.
- Eight platforms spanning phones, surveillance, and automotive were tested.
- Extreme darkening hit 50.0% on iPhone 16 Pro and 33.7% on Wyze.
- OpenPilot cone-region frames darkened severely in 23.0% of frames.
- An exposure-rejection defense cut brightness deviation by 79.16%.
Full article245 words · extracted from arxiv.org · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.37742