A reinforcement-learning attack using a memory-and-reset 'Forget' process fools classifiers and object detectors by modifying fewer than 0.1% of pixels, with fewer queries than prior query-based attacks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
A reinforcement-learning attack using a memory-and-reset 'Forget' process fools classifiers and object detectors by modifying fewer than 0.1% of pixels, with fewer queries than prior query-based attacks.