Talk by Andrew Honig. Ex-Google Security Head. Ex-NSA. Author of Practical Malware Analysis. LinkedIn

DISSERTATION DEFENSE
Department of Computer Science and Engineering

University of South Carolina

Author : Vipula Rawte
Advisor: Dr. Amit Sheth
Date: March 18, 2025
Time:  9:00 am – 11:00 am
Place: Zoom and AI Institute, Seminar Room 529
Meeting Link: https://sc-edu.zoom.us/j/83442966750
Meeting ID: 834 4296 6750

Abstract

Deception is inherent in human interactions, and AI systems increasingly exhibit similar tendencies, mainly through hallucinations - plausible yet incorrect outputs stemming from their design, memory limitations, and statistical nature. As AI progresses into Wave 2 - Generative AI, as outlined by Mustafa Suleyman in The Coming Wave, models like GPT and DALL-E are revolutionizing fields like healthcare and education. However, their rapid adoption brings misinformation, safety, and ethics challenges. Notable cases, such as Air Canada’s chatbot providing false information, highlight the real-world impact of AI hallucinations, a phenomenon so prevalent that hallucinate was named Cambridge Dictionary’s Word of the Year for 2023.

This dissertation tackles AI hallucinations through six key areas: (i) Characterization - developing a taxonomy and benchmark (HILT); (ii) Quantification - introducing evaluation metrics (HVI and HVI_auto); (iii) Detection - proposing a span-based Factual Entailment method to improve accuracy; (iv) Avoidance - creating techniques like “Sorry, Come Again?” (SCA) and [PAUSE] injection for better responses; (v) Mitigation - developing RADIANT, a retrieval-augmented framework for entity-context alignment; and (vi) Multi-modal - constructing VHILT and ViBe datasets for hallucination analysis in image-to-text and text-to-video models. This research makes generative AI more reliable and trustworthy by systematically addressing AI hallucinations.

Below is a tentative agenda for the day. If you plan to attend the luncheon, please RSVP by at this link https://forms.office.com/r/2fayB7SPqA by Tuesday, March 4 to ensure we have an accurate lunch count.

Agenda:
10:00 am - 12:00 pm-  Industrial Advisory Board meeting in room 2277
10:30 am - 12:00 pm-  Even number graduate student poster session, 2nd floor hallway
12:00 pm - 1:30 pm-    Lunch in room 2277

1:30 pm - 2:30 pm-      Industrial Advisory Board meeting continues in room 2277
1:30 pm - 3:00 pm-      Odd number graduate student poster session, 2nd floor hallway
3:00 pm - 4:00 pm -     Talk and poster session winners, room 1400 (1st floor)

Posters:

DISSERTATION DEFENSE

Department of Computer Science and Engineering

University of South Carolina

Abstract

On the internet, where the number of available choices is exponentially growing, there is a need to prioritize and efficiently deliver relevant results to users, on demand. Recommendation systems (RSs) address this need by searching and filtering through large amounts of dynamically generated information and providing users with recommendations tailored to them. These systems have primarily focused on (1) single-user models, where recommendations are tailored towards a specific individual, or (2) single-item models, where items are recommended based on a broader appeal to users and similarities in item metadata, in the past. In many real-world scenarios, however, recommendation systems are often tailored to groups of users rather than individual users. This shift from single-user and towards group recommendation brings forth unique challenges such as addressing the diverse needs of a group, resolving conflicts and reaching consensus, assuring that groups receive fair recommendations without bias towards protected characteristics such as race, gender, and socioeconomic status; and ensuring that recommendations remain stable and adaptable even in response to dynamic and evolving environments. Such systems are growing increasingly relevant in disciplines such as team management, healthcare, online communities, and entertainment.

This dissertation explores and addresses the unique challenges of group recommendation systems (GRSs), such as increased computational complexity, varying group dynamics, and principles of trustworthy artificial intelligence (AI) related to bias, fairness, and robustness. The research makes contributions towards developing novel methods and metrics for GRSs, evaluating them with respect to performance through real-world case studies, such as team formation (project management) and meal planning (healthcare), and improving fairness and robustness of group recommendations. For team recommendation, the built system, called ULTRA, has been evaluated to demonstrate its effectiveness and generality in the context of research funding at academic institutions in the United States (US) and India. This work releases comprehensive datasets to aid in developing adaptable and reliable GRSs that optimize both performance and user satisfaction in dynamic environments. Beyond research, the dissertation is opening new avenues in entrepreneurship, intellectual property, and teaching resources.

DISSERTATION DEFENSE

Department of Computer Science and Engineering

University of South Carolina

Abstract

  Wireless networks have become an integral aspect of our daily lives. Over the years, earlier generations of wireless networks have enabled some innovative applications, such as wireless gaming, fast internet browsing, and home automation, which were previously unattainable. However, to support emerging technologies like autonomous driving, virtual reality, telemedicine, and intelligent manufacturing, which require high data throughput and low latency, there is a need for advanced wireless networks. Legacy networks like WiFi/LTE, which operate below 6 GHz, have limited bandwidth and are insufficient to fulfill the high data throughput demands of several applications.

Millimeter-wave (mmWave) networks, operating between 30 GHz to 300 GHz, promise to offer a broader contiguous spectrum and low latency and might solve various applications’ data throughput and latency requirements. However, due to the directional nature of mmWave, it is prone to frequent outages while using Line-of-Sight (LoS) paths only, and the network deployment needs to consider Non-Line-of-Sight (NLoS) paths to provide reliable network connectivity. Additionally, due to the high operating frequency of mmWave network devices, these devices can also work as sensors to detect objects in their surroundings and work in all weather conditions. However, the specularity of mmWave and the weak reflectivity of objects cause most object details to be lost, making objects imperceptible. Besides, sharing a single mmWave device for networking and sensing applications reduces data throughput and sensing accuracy.

In this dissertation, we first design and evaluate a deep learning-based model to find optimal locations of 5G base stations (called “picocell”) for indoor and outdoor environments. Due to the lack of open-source data samples at high frequency, we collect actual data samples and verify our deep-learning models. Our model uses semantic features of the environment, such as the wall, ceiling, floor, and door, to make it generalizable and requires only a few data samples from the new environment to fine-tune, and it removes the need for an extensive site survey for optimal deployment. We then enable accurate sensing and high-throughput networking with a single mmWave device. We use conditional Generative Adversarial Networks to get an accurate depth image of the objects and residual networks to predict unobservable data samples from previously observed ones during networking. Finally, we design and implement a deep learning framework to detect the 3D bounding boxes of vehicles and pedestrians from mmWave devices in harsh weather conditions and compare their performance with vision-based methods. We use the non-anchor bounding box prediction method to enable 3D object detection for outdoor environments.

DISSERTATION DEFENSE

Department of Computer Science and Engineering
University of South Carolina
Author : Pingping Cai
Advisor: Dr. Song Wang

Abstract

  3D computer vision is a promising research field with the potential to revolutionize future lifestyles. Among various 3D representation formats, point clouds stand out for their efficiency in depicting 3D objects using a set of coordinates, enabling advancements in fields such as autonomous driving, virtual reality, and robotics. Due to the limitations of sensor fields of view and scanning trajectories, the collected point clouds are usually sparse, noisy, and incomplete, impeding the performance of many downstream applications. Thus, the tasks of low-level point cloud processing are proposed to refine and generate dense, clean, and complete point clouds.

You are invited to attend an AI Roundtable event this Friday, November 1. This event is entitled “Ethical and effective use of AI in academic settings. How should we use AI effectively in our classrooms?”

We will have representatives from various departments across campus (Law/Academic Integrity/Library Sciences) and the panel will discuss the use of Gen AI in classrooms. You will have the opportunity to provide feedback to them as both faculty and students.

If you are interested in attending, please register here: https://forms.office.com/r/n4UznxruNg

Held online and in person at the AI Institute 
Room 513, 1112 Greene St. Columbia, SC 29208 (Science and Technology Building)
10 am ET to 12 PM ET (refreshments will be provided)

*Limited to 50 in-person participants

DISSERTATION DEFENSE

Department of Computer Science and Engineering

University of South Carolina

Author : Fengyao Yan

Advisor : Dr. Yan Tong, Dr. Jijun Tang

Date : Oct 24th, 2024

Time:  9:30 am

Place : Zoom Meeting

Link: https://us05web.zoom.us/j/82857019481?pwd=ueKsnxBVTLySbXb4yj4Z93pAzb7va…

Meeting ID: 828 5701 9481
Passcode: 747882

One tap mobile
+12532158782,,82857019481#,,,,*747882# US (Tacoma)
+13462487799,,82857019481#,,,,*747882# US (Houston)

Dial by your location
• +1 253 215 8782 US (Tacoma)
• +1 346 248 7799 US (Houston)
• +1 669 444 9171 US
• +1 669 900 9128 US (San Jose)
• +1 719 359 4580 US
• +1 253 205 0468 US
• +1 507 473 4847 US
• +1 564 217 2000 US
• +1 646 558 8656 US (New York)
• +1 646 931 3860 US
• +1 689 278 1000 US
• +1 301 715 8592 US (Washington DC)
• +1 305 224 1968 US
• +1 309 205 3325 US
• +1 312 626 6799 US (Chicago)
• +1 360 209 5623 US
• +1 386 347 5053 US

Meeting ID: 828 5701 9481
Passcode: 747882

Find your local number: https://us05web.zoom.us/u/leCEnSLjPT

Abstract

      Genes can be treated as a graph that can be mapped. Tremendous information is coded in genes to ensure a complex functioning organism. Decoding this information is critical to understanding our biology and developing treatments for various diseases including cancer. Deep learning, a new branch of computer science, has gained traction over the past decade. It offers more insight into the data that is processed by the deep-learning models. Our study has shown that deep-learning models can be an effective tool in decoding genetic data such as gene tissue-deconvolution, gene graph mapping and genomic imputation. In tasks such as tissue deconvolution, our research has demonstrated the superior capability of deep learning-based approaches in capturing sample variations compared to traditional numerical analytical methods. While our approach requires large relevant datasets for effective deep learning training, this challenge can be addressed with increasing data availability. In gene graphing and mapping, our Graph Neural Network based approach consistently outperforms traditional regression techniques by a significant margin. The primary challenge here lies in the demand for substantial computing resources; however, the ongoing growth in average computing power and the enhanced accessibility of computational resources are expected to alleviate this constraint over time. Moreover, in the realm of generating and imputing missing biological data, cutting-edge generative AI models have proven to be invaluable. We are actively exploring the potential of generative AI to aid in imputing common missing biological data such as gene expression or methylation states. Overall, the evolution of advanced deep learning models has introduced fresh perspectives and possibilities to the field of biology and medicine, albeit accompanied by certain challenges. By addressing these challenges, deep learning models exhibit remarkable efficacy in resolving complex biomedical issues. In the foreseeable future, these advancements hold the promise of unveiling novel biological insights and facilitating the development of innovative treatments, thereby propelling biomedical research forward and ultimately benefiting humanity.