Trojan

About: Trojan is a research topic. Over the lifetime, 2028 publications have been published within this topic receiving 33209 citations.

Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification.

Abstract: Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a certain pattern called trigger, causing misclassification. Many existing trojan attacks have their triggers being input space patches/objects (e.g., a polygon with solid color) or simple input transformations such as Instagram filters. These simple triggers are susceptible to recent backdoor detection algorithms. We propose a novel deep feature space trojan attack with five characteristics: effectiveness, stealthiness, controllability, robustness and reliance on deep features. We conduct extensive experiments on 9 image classifiers on various datasets including ImageNet to demonstrate these properties and show that our attack can evade state-of-the-art defense.

Digital tablets: a Trojan virus for IT in education?

Abstract: IT, still now, has not really entered classrooms because its use constitutes a work overload for teachers. It requires several breaks that teachers must manage: breaks in time, in space and in pedagogy. Digital tablets avoid all those breaks; this is why they should be soon omnipresent in classrooms. Therefore, we have to try, right now, to see how this will change the educational landscape and how the roles of students and teachers should evolve.

Research and practice on the cooperative concealing technology of Trojan horses

Abstract: Trojan is a Trojan horse hiding technology, one of the key technologies, directly determine the viability of Trojan horses This paper describes the current commonly used Trojan horse hiding technology, the traditional implementation method Trojan hidden lack of independence, according to concerted hidden thought, given the four threading model under Windows systems and their specific implementation method to explain the problems encountered in the implementation process and solution approach In response to the four further threading model is just to restore the initial state of the shortcomings of the passive given extension model Experiments show that the four threads together more independent thought hidden Trojan horse has a better prospect

Hardware Trojan Insertion and Detection in Asynchronous Circuits

Abstract: Hardware Trojan threats caused by malicious designers and untrusted manufacturers have become one of serious issues in modern VLSI systems. In this paper, we show some experimental results to insert hardware Trojans into asynchronous circuits. As a result, the overhead of hardware Trojan insertion in asynchronous circuits may be small for malicious designers who have enough knowledge about the asynchronous circuits. In addition, we also show several Trojan detection methods using deep learning schemes which have been proposed to detect synchronous hardware Trojan in the netlist level. We apply them to asynchronous hardware Trojan circuits and show their results. They have a great potential to detect a hardware Trojan in asynchronous circuits.