DETOUR enables practical backdoor attacks on object detectors by training with rescaled semantic triggers from real-world objects placed at multiple locations to exploit the trigger radiating effect for reliable activation under varying fields of view and spatial configurations.
Neural Networks 61, 85–117 (Jan 2015) DETOUR: A Practical Backdoor Attack against Object Detection 23
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DETOUR: A Practical Backdoor Attack against Object Detection
DETOUR enables practical backdoor attacks on object detectors by training with rescaled semantic triggers from real-world objects placed at multiple locations to exploit the trigger radiating effect for reliable activation under varying fields of view and spatial configurations.