My academic journey at Binghamton University has been a transformative exploration in deep learning
and IoT. As I delved into this rapidly progressing field, I identified a burgeoning challenge: the increasing
security risks inherent in deep learning technologies. This realization spurred me to investigate these vulnerabilities,
leading to a collaborative research effort. Our findings were encapsulated in the paper “Secure
Source Free Domain Adaptation,” which I had the honor of co-authoring. This paper was subsequently
presented at the International Conference on Computer Vision (ICCV), a highly respected conference in our
field.
In addition to this research, my Master’s thesis is centered around the development of real-time data
analytics, where I have incorporated Real Time Object Detection using raspberry pi. The system is being used to detect spotted lantern fly in the wild.
Alongside these endeavors, I took the opportunity to further refine my smart stick project, initially developed during my undergraduate studies. For the
Introduction to IoT course, I evolved the project, now named "Third Eye," by integrating continuous connectivity using LoRa technology.
A DNN for Detecting Spotted Lanternflies Using Energy Efficient WAN
Detecting invasive species like the Spotted Lanternfly (SLF) in remote and hard-to-reach places such as tree
branches or tall building walls is labor-intensive and leads to significant crop
losses. To tackle this, we developed a new system, a Deep Neural Network (DNN)
architecture that incorporates MobileNet V3, optimized for low-power devices and
trained on a dedicated SLF dataset. Deployed on a Raspberry Pi Model B with a
LoRa module, our system is energy-efficient and operates effectively on edge devices
with limited computational resources through quantization, achieving high accuracy
and low latency for detection. Our results demonstrate that our system covers a
larger area and consumes significantly less power than other network technologies
such as WiFi and Bluetooth, making it a superior solution for managing invasive
species in expansive, resource-limited environments
Adaptive Real Time Object Detection using advance optical flow algorithm
We are developing a real-time object detection system that can adapt to changes in the environment. We are using optical flow to detect changes in the environment, and then using this information to adapt the object detection model to the new environment.
Investigating Linear Neural Network’s Vulnerability
In this research, the primary objective is to investigate the effect of elimination of non linear activation in the
DNN in terms of robustness. We have shown that the linear neural network is vulnerable to adversarial attacks.
Security Threat in Source Free Domain Adaptation
We investigated the effect of a source adversary which may inject a hidden malicious behavior
(Backdoor/Trojan) during source training and potentially transfer it to the target domain even after benign
training by the victim (target do-main owner). We also built a defense method for the attack as well.
Weight Pruning
We investigated the effect of weight pruning in unsupervised learning setup. We also proposed a weight
perturbation method. We showed that the weight pruning is very effective in unsupervised learning setup.
Local features detection using 3D point cloud
We built a pipeline to detect local features using 3D point cloud. The pipeline consists of Kmeans clustering
algorithm to first segment the point cloud and then we used the Gaussian Mixture Model to get the local features.
We then ran the pipeline on the 3D point cloud of the face and got the local features.
