Session: Adversarial attacks and defense mechanisms against deep point processes
Adversarial attacks and defense mechanisms against deep point processes are a matter of trustworthy ai and machine learning. In this research, accuracy, cybersecurity, and trust come together. More recently, neural network-based approaches to modeling point processes have received attention from the research community. These methods attempt to learn non-parametrically key components of point processes and their intensity to capture real event patterns better than parametric models. However, deep learning approaches run the risk of overparameterizing models and overfitting noisy real-world data. In addition, there is a lack of research into how robust such models are to natural shocks to systems, e.g., how a pandemic impacts deep point process forecasts of crime and adversarial attacks. My research focuses on modeling stochastic point processes using deep learning approaches and examining their robustness against natural shocks and adversarial attacks.
- Adversarial attacks and defense mechanisms against deep point processes are a matter of trustworthy ai and machine learning.
- Adversarial Attack is an important step towards understanding the deep learning models
Samira Khorshidi is a computer science Ph.D. candidate and graduate research assistant at Indiana University-Purdue University, Indianapolis (IUPUI), a member of IEEE, ACM, and Executive Committee member of women in Computer science at IUPUI. She has also been the teaching assistant of data science and deep learning courses at IUPUI since 2019. Samira is a skilled problem solver with a solid background in machine learning and pattern recognition using R, Python, and Matlab. In addition, she has seven years of industry experience in database and software development and is a co-founder of the monthly meetup series (Lou-AI). Her research area is trustworthy machine learning, and her Ph.D. thesis is focused on adversarial attacks and defense mechanisms. Up to date, Samira has published several NSF-supported journal and conference papers and served as a reviewer for multiple conferences. Her ultimate goal is to pursue applied research in responsible and trustworthy AI, and as an instructor, encourage females to enter, study, and graduate in computer science.