Jedi: Entropy-based Localization and Removal of Adversarial Patches
This addresses security vulnerabilities in real-world AI systems against adversarial attacks, with incremental improvements over existing defenses.
The paper tackles the problem of defending against adversarial physical patches in computer vision by proposing Jedi, a model-agnostic defense that uses entropy analysis and an autoencoder for localization and removal, achieving detection of 90% of patches and recovery of up to 94% of attacks.
Real-world adversarial physical patches were shown to be successful in compromising state-of-the-art models in a variety of computer vision applications. Existing defenses that are based on either input gradient or features analysis have been compromised by recent GAN-based attacks that generate naturalistic patches. In this paper, we propose Jedi, a new defense against adversarial patches that is resilient to realistic patch attacks. Jedi tackles the patch localization problem from an information theory perspective; leverages two new ideas: (1) it improves the identification of potential patch regions using entropy analysis: we show that the entropy of adversarial patches is high, even in naturalistic patches; and (2) it improves the localization of adversarial patches, using an autoencoder that is able to complete patch regions from high entropy kernels. Jedi achieves high-precision adversarial patch localization, which we show is critical to successfully repair the images. Since Jedi relies on an input entropy analysis, it is model-agnostic, and can be applied on pre-trained off-the-shelf models without changes to the training or inference of the protected models. Jedi detects on average 90% of adversarial patches across different benchmarks and recovers up to 94% of successful patch attacks (Compared to 75% and 65% for LGS and Jujutsu, respectively).