Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes
This addresses the vulnerability of DNN-based vision systems to adversarial examples, offering a generalizable solution for practical multi-object scenes.
The paper tackles the problem of detecting adversarial attacks in vision systems by exploiting object co-occurrence relationships in complex scenes, achieving high accuracy with a method independent of the deployed object detector.
Vision systems that deploy Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Recent research has shown that checking the intrinsic consistencies in the input data is a promising way to detect adversarial attacks (e.g., by checking the object co-occurrence relationships in complex scenes). However, existing approaches are tied to specific models and do not offer generalizability. Motivated by the observation that language descriptions of natural scene images have already captured the object co-occurrence relationships that can be learned by a language model, we develop a novel approach to perform context consistency checks using such language models. The distinguishing aspect of our approach is that it is independent of the deployed object detector and yet offers very high accuracy in terms of detecting adversarial examples in practical scenes with multiple objects.