• Publications
  • Influence
A Game Theoretic Approach to Strategy Generation for Moving Target Defense in Web Applications
TLDR
The present complexity in designing web applications makes software security a difficult goal to achieve. Expand
  • 33
  • 5
  • PDF
MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense
TLDR
We propose a meta-defense for 'boosting' the robustness of an ensemble of deep neural networks (DNNs) for visual classification tasks against adversarial attacks. Expand
  • 19
  • 5
  • PDF
A Survey of Moving Target Defenses for Network Security
TLDR
We analyze the recent advancements made in the development of MTDs and highlight (1) how these defenses can be defined using common terminology, (2) can be made more effective with the use of artificial intelligence techniques for decision making, (3) be implemented in practice and (4) evaluated. Expand
  • 13
  • 2
  • PDF
RADAR - A Proactive Decision Support System for Human-in-the-Loop Planning
TLDR
We investigate the extent to which an automated Figure 1: Planning for decision support involves iterative and the need to consider difference of models between the planner and the human in the loop. Expand
  • 29
  • 1
  • PDF
Moving Target Defense for Web Applications using Bayesian Stackelberg Games: (Extended Abstract)
TLDR
We present a way to find effective switching strategies by modeling this ecosystem as a Bayesian Stackelberg game with the administrator as the leader and the hackers as the followers, which as we show succinctly captures various aspects of the Moving Target Defense systems. Expand
  • 27
  • 1
  • PDF
Securing Deep Neural Nets against Adversarial Attacks with Moving Target Defense
TLDR
We propose to use the concept of Moving Target Defense (MTD) for increasing the robustness of well-known deep networks trained on the ImageNet dataset towards such adversarial attacks. Expand
  • 7
  • 1
MTDeep: Moving Target Defense to Boost the Security of Deep Neural Networks Against Adversarial Attacks
Present attack methods can make state-of-the-art classification systems based on deep neural networks mis-classify every adversarially modified test example. The design of general defense strategiesExpand
  • 3
  • 1
  • PDF
Moving Target Defense for the Placement of Intrusion Detection Systems in the Cloud
TLDR
A lot of software systems are deployed in the cloud. Expand
  • 13
  • PDF
Markov Game Modeling of Moving Target Defense for Strategic Detection of Threats in Cloud Networks
TLDR
The processing and storage of critical data in large-scale cloud networks necessitate the need for scalable security solutions. Expand
  • 11
  • PDF
Imagining an Engineer: On GAN-Based Data Augmentation Perpetuating Biases
TLDR
We show that GAN-based data augmentation can propagate the biases inherent in the training data, and sometimes, even amplify them. Expand
  • 5
  • PDF