Detection Mechanisms of One-Pixel Attack

In recent years, a series of researches have revealed that the Deep Neural Network (DNN) is vulnerable to adversarial attack, and a number of attack methods have been proposed. Among those methods, an extremely sly type of attack named the one-pixel attack can mislead DNNs to misclassify an image via only modifying one pixel of the image, leading to severe security threats to DNN-based information systems. Currently, no method can really detect the one-pixel attack, for which the blank will be filled by this paper. This paper proposes two detection methods, including trigger detection and candidate detection. The trigger detection method analyzes the vulnerability of DNN models and gives the most suspected pixel that is modified by the one-pixel attack. The candidate detection method identifies a set of most suspected pixels using a differential evolution-based heuristic algorithm. The real-data experiments show that the trigger detection method has a detection success rate of 9.1%, and the candidate detection method achieves a detection success rate of 30.1%, which can validate the effectiveness of our methods.

Employing Long Short-Term Memory Networks in Trigger Detection for Emetophobia

Research focused on mental health-related issues is vital to the modern person’s life. Specific phobias are part of the anxiety disorder umbrella and they are distressing afflictions. Emetophobia is the rarely known, yet fairly common and highly disruptive specific phobia of vomiting. Unlike other phobias, emetophobia is triggered not only by the object of the specific fear, but also by verbal and written mentions of said object. This paper proposes and compares ten neural network-based architectures that discern between triggering and non-triggering groups of written words. An interface is created, where the best models can be used in emetophobia-related applications. This interface is then integrated into an application that can be used by emetophobes to censor online content such that the exposure to triggers is controlled, patient-centered, and patient-paced.