LOGICDEF: An Interpretable Defense Framework against Adversarial Examples via Inductive Scene Graph Reasoning

Abstract

Deep vision models have provided new capability across a spectrum of applications in transportation, manufacturing, agriculture, commerce, and security. However, recent studies have demonstrated that these models are vulnerable to adversarial attack, exposing a risk-of-use in critical applications where untrusted parties have access to the data environment or even directly to the sensor inputs. Existing adversarial defense methods are either limited to specific types of attacks or are too complex to be applied to practical vision models. More importantly, these methods rely on techniques that are not interpretable to humans. In this work, we argue that an effective defense should produce an explanation as to why the system is attacked, and by using a representation that is easily readable by a human user, e.g. a logic formalism. To this end, we propose logic adversarial defense (LogicDef), a defense framework that utilizes the scene graph of the image to provide a contextual structure for detecting and explaining object classification. Our framework first mines inductive logic rules from the extracted scene graph, and then uses these rules to construct a defense model that alerts the user when the vision model violates the consistency rules. The defense model is interpretable and its robustness is further enhanced by incorporating existing relational commonsense knowledge from projects such as ConceptNet. In order to handle the hierarchical nature of such relational reasoning, we use a curriculum learning approach based on object taxonomy, yielding additional improvements to training and performance.

Robust appearance modeling for object detection and tracking: a survey of deep learning approaches

“…In LOGICDEF (Figure 8), Yang et al [109] are inspired by the fact that the human visual system easily detects incoherent scenes by mining contextual cues from a powerful scene representation that organizes its elements in a structured hierarchy of objects and their relationships. From a scene graph, LOGICDEF extracts logic rules about objects and their relationships and combines this information with commonsense knowledge derived from Con-ceptNet [110]-a large commonsense knowledge graph of frequently-used words and phrases collected from diverse sources-to enforce contextual consistency constraints over the scene elements.…”

“…Left: The adversarial patch printed on the train causes a deep learning classifier to misclassify it as a cat. But, using logical context (Right), LOGICDEF [109] correctly discovers that the object must be a train…”