• UCF Predictive Analytics Innovation Fellow (2017-2018)
  • Air Force Office of Scientific Research Young Investigator Award (2016-2019)
  • UCF Faculty Senate (2016-2017)
  • National Science Foundation Computing and Communications Foundations -- Exploiting Parallelism & Scalability (2014-2017)
  • National Science Foundation Computing and Communications Foundations -- Software & Hardware Foundations (2014-2018)
  • Best Paper Award at IEEE International Conference on Computational Advances in Bio and Medical Sciences ICCABS (2014)
  • ASE/Air Force Summer Faculty Fellowship (2014)
  • Charles N. Millican Faculty Fellow (2013)
  • IEEE Orlando Outstanding Engineering Educator Award (2013)
  • Air Force Information Directorate Visiting Faculty Fellowship Program (2013)
  • Best Paper Award at IEEE International Conference on Computational Advances in Bio and Medical Sciences ICCABS (2011)

Recent Publications

D. Chakraborty, S. Raj, J. C. Gutierrez, T. Thomas, and S. K. Jha, “ In-Memory Execution of Compute Kernels using Flow-based Memristive Crossbar Computing ,” in IEEE International Conference on Rebooting Computing 2017, Washington D.C., Forthcoming.Abstract


Rebooting computing using in-memory architectures relies on the ability of emerging devices to execute a legacy software stack. In this paper, we present our approach of executing compute kernels written in a subset of the C pro- gramming language using flow-based computing on nanoscale memristor crossbars. Our framework also tests the correctness of the design using the parallel Xyces electronic simulation software. We demonstrate the potential of our design methodology by designing and testing a compute kernel for edge detection in images. 


S. Raj, A. Ramanathan, L. L. Pullum, and S. K. Jha, “ Testing Autonomous Cyber-Physical Systems using Fuzzing Features Derived from Convolutional Neural Networks ,” in ACM SIGBED International Conference on Embedded Software (EMSOFT), Seoul, South Korea, 2017.Abstract


Autonomous cyber-physical systems rely on modern machine learning methods such as deep neural networks to control their interactions with the physical world. Testing of such intelligent cyber-physical systems is a challenge due to the huge state space associated with high-resolution visual sensory inputs. In this paper, we demonstrate how fuzzing the input using patterns obtained from the convolutional lters of an unrelated convolutional neural network can be used to test the correctness of vision algorithms implemented in intelligent cyber-physical systems. Our method discovers interesting counterexamples to the pedestrian detection algorithm implemented in the popular OpenCV library. Our approach also unearths counterexamples to the correct behavior of an autonomous car similar to NVIDIA’s end-to-end self-driving deep neural net running on the Udacity open-source simulator. 


S. Raj, S. K. Jha, L. L. Pullum, and A. Ramanathan, “ SATYA: Defending against Adversarial Attacks using Statistical Hypothesis Testing ,” in The 10th International Symposium on Foundations and Practice of Security (FPS 2017), Nancy, France, 2017.Abstract

The paper presents a new defense against adversarial attacks for deep neural networks. We demonstrate the effectiveness of our approach against the popular adversarial image generation method DeepFool. Our approach uses Wald's Sequential Probability Ratio Test to sufficiently sample a carefully chosen neighborhood around an input image to determine the correct label of the image. On a benchmark of 50,000 randomly chosen adversarial images generated by DeepFool we demonstrate that our method SATYA is able to recover the correct labels for 95.76% of the images for CaffeNet and 97.43% of the correct label for GoogLeNet. 

A. Ramanathan, L. L. Pullum, S. Raj, Z. Husein, S. Pattanaik, and S. K. Jha, “ Adversarial attacks on computer vision algorithms using natural perturbations ,” in Tenth International Conference on Contemporary Computing, New Delhi, India, 2017, pp. in press.Abstract


Verifying the correctness of intelligent embedded systems is notoriously difficult due to the use of machine learning algorithms that cannot provide guarantees of deterministic correctness. In this paper, we investigate the histogram of oriented gradients (HOG) based human detection algorithm implemented in the popular OpenCV computer vision framework. Our validation efforts demonstrate that the OpenCV imple- mentation is susceptible to errors due to both malicious perturbations and naturally occurring fog phenomena. To the best of our knowledge, we are the first to explicitly employ a natural perturbation (like fog) as an adversarial attack using methods from computer graphics and demonstrate that computer vision algorithms are also susceptible to errors under such naturally occurring minor perturbations. Our methods and results may be of interest to the designers, developers and validation teams of intelligent cyber-physical systems such as autonomous cars. 


D. Chakraborty, S. Raj, and S. K. Jha, “ A Compact 8-bit Adder Design using In-Memory Memristive Computing: Towards Solving the Feynman Grand Prize Challenge ,” in 13th ACM/IEEE International Symposium on Nanoscale Architectures, Newport, USA, 2017, pp. in press.Abstract

We introduce a new compact in-memory computing design for implementing 8-bit addition using eight vertically-stacked nanoscale crossbars of  one-diode one-memristor 1D1M switches. Each crossbar in our design only has 5 rows and 4 columns. Hence, the design may be used to fabricate a compact 8-bit adder that meets the size constraint of  50nm x 50nm x 50nm imposed by the electrical component of the Feynman Grand Prize. The potential availability of sub-5nm nanoscale memristors and single-molecule diode devices coupled with the ability to fabricate high-density nanoscale memristor crossbars suggests that our design may eventually be fabricated to meet the size constraints of the  Feynman Grand Prize.

A. Velasquez and S. K. Jha, “ Computation of Boolean Matrix Chain Products in 3D ReRAM ,” in IEEE International Symposium on Circuits and Systems (ISCAS), Baltimore, MD, 2017, pp. 2643-2646.Abstract


Energy concerns, the infamous memory wall, and the enormous data deluge of the current big-data age have made the integration of processing and memory elements into a very appealing paradigm. In this paper, we focus on a computation-in- memory solution to the problem of multiplying a set of Boolean matrices, also known as Boolean matrix chain multiplication (BMCM). This is a fundamental computational task with applica- tions in graph theory, group testing, data compression, and digital signal processing. In particular, we propose a framework for mapping arbitrary instances of BMCM to a 3-dimensional (3D) crossbar memory architecture consisting of 1-diode 1-resistor (1D1R) structures. 


D. Chakraborty and S. K. Jha, “ Design of Compact Memristive In-Memory Computing Systems using Model Counting ,” in IEEE International Symposium on Circuits and Systems (ISCAS)., Baltimore, MD, 2017, pp. 2655-2658.Abstract


Crossbars of nanoscale memristors are being fab- ricated to serve as high-density non-volatile memory devices. The flow of current through memristor crossbars has been recently used to perform in-memory computations. However, existing approaches based on decision procedures only scale to the simplest circuits such as one-bit adders and other approaches employing decision diagrams produce large crossbar designs. 

In this paper, we present a new method for synthesizing 3 compact combinational circuits using nanoscale crossbars. Our synthesis procedure exploits a symbolic representation of Boolean functions and employs model counting to guide a simulated annealing based search procedure. 



S. Raj, S. K. Jha, L. L. Pullum, and A. Ramanathan, “ Statistical Hypothesis Testing using CNN Features for Synthesis of Adversarial Counterexamples to Human and Object Detection Vision Systems ,” Oak Ridge National Laboratory Technical Report, vol. ORNL/LTR-2017/118. 2017. Publisher's VersionAbstract


Validating the correctness of human detection vision systems is crucial for safety applications such as pedestrian collision avoidance in autonomous vehicles. The enormous space of possible inputs to such an intelligent system makes it difficult to design test cases for such systems. In this paper, we present our tool MAYA that uses an error model derived from a convolutional neural network (CNN) to explore the space of images similar to a given input image, and then tests the correctness of a given human or object detection system on such perturbed images. We demonstrate the capability of our tool on the pre-trained Histogram-of- Oriented-Gradients (HOG) human detection algorithm implemented in the popular OpenCV toolset and the Caffe object detection system pre-trained on the ImageNet benchmark. Our tool may serve as a testing resource for the designers of intelligent human and object detection systems. 


S. Raj, et al., “ A theorem proving approach for automatically synthesizing visualizations of flow cytometry data ,” BMC Bioinformatics, vol. 18, no. 8, pp. 245, 2017. Publisher's VersionAbstract

Polychromatic flow cytometry is a popular technique that has wide usage in the medical sciences, especially for studying phenotypic properties of cells. The high-dimensionality of data generated by flow cytometry usually makes it difficult to visualize. The naive solution of simply plotting two-dimensional graphs for every combination of observables becomes impractical as the number of dimensions increases. A natural solution is to project the data from the original high dimensional space to a lower dimensional space while approximately preserving the overall relationship between the data points. The expert can then easily visualize and analyze this low-dimensional embedding of the original dataset.