CSE 600 Talk: Securing Software-Defined Networking Infrastructure by Dr. Guofei Gu

ABSTRACT: Today's network and computing infrastructure rests on inadequate  foundations. An emerging, promising new foundation for computing is software-defined infrastructure (SDI), which offers a range of  
technologies including: compute, storage and network virtualization;  novel separation of concerns at the systems level; and new approaches to system and device management. As a representative example of SDI,  
software-defined networking (SDN) is a new networking paradigm that decouples the control logic from the closed and proprietary implementations of traditional network data plane infrastructure. SDN is now becoming the networking foundation for data-center/cloud, future Internet and 5G infrastructures.  

We believe that SDN is an impactful technology to drive a variety of innovations in network management and security. It is now clear that security will be a top concern, as well as a new killer app, for SDN. In this talk, I will discuss some new opportunities, as well as challenges, in this new direction and demonstrate with our recent  
research results. I will discuss how SDN can enhance network security. And I will also discuss some unique new security problems inside SDN and introduce some of our work to enhance the security of SDN. Finally, I will share my vision on programmable system security in a software-defined world.  

BIO: Dr. Guofei Gu is a professor in the Department of Computer Science & Engineering at Texas A&M University (TAMU). Before coming to Texas A&M, he received his PhD degree in Computer Science from the College  
of Computing, Georgia Institute of Technology. His research interests are in network and systems security.  
Dr. Gu is a recipient of 2010 NSF CAREER Award, 2013 AFOSR Young  Investigator Award, 2010 IEEE S&P Best Student Paper Award, 2015 ICDCS Best Paper Award, Texas A&M Dean of Engineering Excellence Award,  
Presidential Impact Fellow, Charles H. Barclay Jr. '45 Faculty Fellow and the Google Faculty Research Award. He is an active member of the security research community and has pioneered several new research directions such as botnet detection/defense and SDN security. Dr. Gu has served on the program committees of top-tier security conferences such as IEEE S&P, ACM CCS, USENIX Security and NDSS. He is an ACM Distinguished Member, an Associate Editor for IEEE Transactions on Information Forensics and Security (T-IFS), and the Steering Committee co-chair for SecureComm. He is currently directing the SUCCESS Lab at TAMU.
Predictable Autonomy for Cyber-Physical Systems by Stanley Bak, Safe Sky Analytics

ABSTRACT: Cyber-physical systems combine complex physics with complex software. Although these systems offer significant potential in fields such as smart grid design, autonomous robotics and medical systems, verification of CPS designs remains challenging. Model-based design permits simulations to be used to explore potential system behaviors, but individual simulations do not provide full coverage of what the system can do. In particular, simulations cannot guarantee the absence of unsafe behaviors, which is unsettling as many CPS are safety-critical systems.

The goal of set-based analysis methods is to explore a system's behaviors using sets of states, rather than individual states. The usual downside of this approach is that set-based analysis methods are limited in scalability, working only for very small models. This talk describes our recent process on improving the scalability of set-based reachability computation for LTI hybrid automaton models, some of which can apply to very large systems (up to one billion continuous state variables!). Lastly, we'll discuss the significant overlap of techniques used for our scalable reachability analysis methods with set-based input/output analysis of neural networks.

BIO: Stanley Bak is a computer scientist investigating the predictable design of autonomous cyber-physical systems. He strives to develop practical formal methods that are both scalable and useful, which demands developing new theory, programming efficient tools and building experimental systems. He received a Bachelor's degree in Computer Science from Rensselaer Polytechnic Institute (RPI) in 2007 (summa cum laude), and a Master's degree in Computer Science from the University of Illinois at Urbana-Champaign (UIUC) in 2009. He completed his PhD from the Department of Computer Science at UIUC in 2013. He received the Founders Award of Excellence for his undergraduate research at RPI in 2004, the Debra and Ira Cohen Graduate Fellowship from UIUC twice, in 2008 and 2009, and was awarded the Science, Mathematics and Research for Transformation (SMART) Scholarship from 2009 to 2013. From 2013 to 2018, Stanley was a Research Computer Scientist at the US Air Force Research Lab (AFRL), both in the Information Directorate in Rome, NY, and in the Aerospace Systems Directorate in Dayton, OH. He currently helps run Safe Sky Analytics, a research consulting company investigating verification and autonomous systems, and performs teaching as an Adjunct Professor at Georgetown University.
Abstract: Language is not just something we generate, but something humans use to interact with the world around them. Indeed, today's conversational AI agents speak fluently, but often treat language as prediction rather than interaction, producing responses that sound correct while failing to recognize when requests are ungrounded, impossible, or misunderstood. My research asks what it would take for multimodal agents to take the next step and use language effectively to take actions in grounded contexts and in this talk, I argue that many challenges in multimodal LLM design, including alignment, hallucination, and adaptation, are due to a lack of pragmatics: an understanding of the implicit context behind the implied actions of the words in the query. From visual understanding, to automatic speech recognition, to hallucination detection, I will demonstrate that incorporating pragmatic/contextual reasoning substantially improves agent behavior, and that pragmatic reasoning will drive a necessary shift in how we build multimodal conversational agents that can see, listen, act, and speak in context.


Bio: David M. Chan, Ph.D., is a postdoctoral scholar at the University of California, Berkeley, specializing in multimodal conversational AI. His research focuses on developing scalable AI systems that move beyond language prediction toward grounded language use, integrating vision, audio, and language to enable pragmatic interaction, improve AI-human collaboration, and reduce hallucinations in generative models. Beyond academia, he has worked with leading organizations including Amazon, Google, and NASA, to build and deploy safe, efficient, and accessible machine learning systems. He is also the developer and maintainer of TSNE-CUDA, an open-source tool for high-dimensional data visualization, used by over 40,000 researchers in fields ranging from biomedical technology to industrial manufacturing. David holds a Ph.D. and M.Sc. in Computer Science from UC Berkeley, where he was a graduate fellow with the Center for Technology, Society & Policy (CTSP), and dual B.Sc. degrees in Computer Science and Mathematics from the University of Denver.

Location: NCS 120

Abstract: Human gaze behavior is a fundamental cue for understanding social intent, human-machine interaction, and cognitive processes. This dissertation addresses the challenges of gaze target estimation (GTE), also known as gaze following, by developing a holistic understanding of gaze across complex environments.
First, we improve GTE performance through Patch-level Distribution Prediction (PDP). Unlike traditional pixel-wise regression, PDP models gaze as a spatial distribution over patches, better accounting for annotation variance and regularizing the pixel-wise heatmap prediction through multi-scale modeling. Second, to mitigate the high cost of data labeling, we present GCDR, the first semi-supervised method for gaze following. By prompting large Visual Question Answering (VQA) models to generate initial Grad-CAM heatmaps and refining them via a diffusion model, GCDR achieves robust performance with minimal human annotation. Third, we expand the applicability of GTE to multi-camera environments. By introducing the Multi-View Gaze Target (MVGT) dataset, along with two novel frameworks for integrating information and predicting gaze targets across views, we explore a new direction that overcomes single-view limitations such as face occlusion and out-of-view targets. Finally, we propose OmniGF, a multi-person gaze following model built on Vision-Language Models (VLMs) that enriches gaze target localization with semantic and social reasoning. By leveraging the semantic capabilities of VLMs alongside structural innovations to ground the model with fine-grained cues for each individual, OmniGF achieves state-of-the-art performance across three gaze following tasks.
Collectively, by tackling the gaze following problem through the distinct yet complementary perspectives of probabilistic modeling, geometric reasoning, and multimodal learning, this dissertation builds a holistic understanding of human gaze, paving the way for more intuitive artificial intelligence systems in downstream applications.

Speaker: Qiaomu Miao

Location: NCS 220
Abstract: In recent years, we have been developing generative AI methods to design increasingly complex objects. Our goal is to improve performance while ensuring that these objects remain controllable. This requires addressing several challenging problems, including:
  • Modeling composite objects in a way that preserves consistency under deformation.
  • Estimating the uncertainty of the surrogate models used to predict performance during optimization.
  • Co-designing objects for both high performance and ease of control.
In this talk, I will present our approach to these challenges and describe end-to-end design pipelines that have the potential to radically transform computer-assisted engineering.

Speaker: Pascal Fua received an engineering degree from Ecole Polytechnique, Paris, in 1984 and a Ph.D. in Computer Science from the University of Orsay in 1989. He joined EPFL (Swiss Federal Institute of Technology) in 1996, where he is a Professor in the School of Computer and Communication Science and head of the Computer Vision Lab. Before that, he worked at SRI International and at INRIA Sophia-Antipolis as a Computer Scientist.
His research interests include shape modeling and motion recovery from images, analysis of microscopy images, and machine learning. He has (co)authored over 400 publications in refereed journals and conferences. He has received several ERC grants. He is an IEEE Fellow and has been an Associate Editor of the IEEE journal Transactions For Pattern Analysis and Machine Intelligence. He often serves as the program committee member, area chair, and program chair of major vision conferences and has cofounded three spinoff companies.

This course is designed to help you approach AI with clarity and intention. Explore how to ask better questions, apply critical judgment to AI-generated outputs, and use these tools to support--not replace--human decision-making. With the right prompts, a thoughtful lens, and a focus on impact, AI can help reduce friction and free you to focus on what matters most: people, purpose, and leadership.

Audience: Any current or aspiring leader who currently uses AI and is interested in bringing their skills to the next level.

Register here.

The Challenges of Machine Learning in Adversarial Settings by Patrick McDaniel, Pennsylvania State University

Abstract: Advances in AI and machine learning have enabled new applications and services to interpret and process inputs in previously unthinkable complex environments. Autonomous cars, data analytics, adaptive communication and self-aware software systems are now revolutionizing markets by achieving or exceeding human performance. In this talk, I consider the evolving use of machine learning in security-sensitive contexts and explore why many systems are vulnerable to nonobvious and potentially dangerous manipulation. Here, we examine sensitivity in any application whose misuse might lead to harm--for instance, forcing adaptive network in an unstable state, crashing an autonomous vehicle or bypassing an adult content filter. I explore the use of machine learning in this area particularly in light of recent discoveries in the creation of adversarial samples and defenses against them and posit on future attacks on machine learning. The talk is concluded with a discussion of the technological and societal challenges we face as a result of current and future advances in intelligent computing.

Bio: Patrick McDaniel is the William L. Weiss Professor of Information and Communications Technology and Director of the Institute for Networking and Security Research in the School of Electrical Engineering and Computer Science at the Pennsylvania State University. Professor McDaniel is also a Fellow of the IEEE and ACM and the director of the NSF Frontier Center for Trustworthy Machine Learning. He also served as the program manager and lead scientist for the Army Research Laboratory's Cyber-Security Collaborative Research Alliance from 2013 to 2018. Patrick's research centrally focuses on a wide range of topics in computer and network security and technical public policy. Prior to joining Penn State in 2004, he was a senior research staff member at AT&T Labs-Research.
Abstract:

Recent advances in deep learning have significantly enhanced the capabilities of Natural Language Processing (NLP) and Vision-Language Models (VLMs). However, these advancements come with increased vulnerabilities, notably through backdoor attacks that pose severe security threats. This thesis addresses two critical dimensions of Trustworthy AI and Efficient Multimodal Representation Learning: (1) security through analyzing, detecting, and designing backdoor attacks in NLP and VLMs, and (2) efficiency through advanced multimodal representation methods tailored for clinical and medical imaging applications.

In the first dimension, we explore the internal mechanisms exploited by backdoor attacks, identifying the distinctive phenomenon of attention focus drifting in compromised transformer models, where trigger tokens consistently hijack attention. Leveraging these insights, we propose robust detection frameworks, including the attention-based Trojan detector (AttenTD) and a task-agnostic logit-based detection method (TABDet), achieving effective identification of backdoored NLP models across diverse tasks. We further introduce novel backdoor attack methodologies: the Trojan Attention Loss (TAL), enhancing attack efficiency and stealth through direct attention manipulation, and BadCLM, demonstrating critical vulnerabilities in clinical decision-support systems by effectively compromising clinical language models.

Extending our security exploration to multimodal settings, we investigate backdoor attacks on Vision-Language Models (VLMs), particularly in complex image-to-text generation tasks, proposing innovative techniques (TrojVLM, VLOOD) capable of embedding backdoors without direct access to original training data, thus showcasing practical risks in real-world scenarios.

In the second dimension, we address efficiency and interpretability challenges in clinical and pathology applications. We introduce TCP-LLaVA, the first multimodal large language model (MLLM) designed explicitly for Whole Slide Image (WSI) Visual Question Answering (VQA). Utilizing a novel token compression mechanism inspired by transformer-based models, TCP-LLaVA substantially reduces computational resource consumption while maintaining superior VQA performance across multiple tumor subtypes. Additionally, we present a multimodal transformer model integrating structured Electronic Health Records (EHR) with clinical notes, demonstrating enhanced predictive accuracy and interpretability for in-hospital mortality prediction through integrated gradient-based interpretability methods.

Together, these contributions present a comprehensive approach to ensuring AI models are not only secure against malicious manipulation but also efficient and interpretable for critical clinical applications, underscoring the essential need for trustworthy and effective AI systems.

Speaker: Weimin Lyu

Zoom: https://stonybrook.zoom.us/j/2392326575?pwd=SVQ2VkFXTnZZYmJUMXgvTXBuZWM3UT09

Meeting ID: 239 232 6575
Passcode: 436192
Title: Class visual similarity based noisy sample removal in generative Few Shot Learning
Time: Thursday, Feb 4, 11:30am - 1:00pm
Zoom:
https://stonybrook.zoom.us/j/8563646526?pwd=anJna1gzUStXNlNVSUIzdDRUSC9CUT09

Meeting ID: 856 364 6526
Passcode: 203791



Abstract:  

Over the past decade, larger datasets, hardware accelerations, and network architecture improvements have contributed to phenomenal achievements in many tasks of computer

vision. However, in the absence of large datasets, computer vision models struggle to learn

general representations which results in poor performance. Few-shot learning tries to address 

this problem by proposing models which learn from a few examples.


I first give an overall review of few-shot learning methods. I particularly focus on generative Few Shot Learning(FSL) methods, which augment the scarce categories in a dataset by generating samples for those rare categories. As the actual class distribution can be complex and lie very close to each other, the sample generated for one class can be noisy or lie close to another class.  However, none of the current FS generative methods perform any form of quality control of the generated samples.


In this work, I propose to identify and remove the generated samples that are less likely to be in the distribution of the few-shot class. Here I particularly deal with few-shot scenarios where the

prior information of the relationship between the classes based on visual  similarity is available. The main idea is to exploit these priors to better identify the unreliable generated samples.


Particularly, I have proposed two methods based on class relationship to detect noisy generated samples. In the first method, we assume that the embedding space of each class follows a Gaussian distribution.  From this assumption, I propose Gaussian Neighborhood (GN), a method to estimate how likely a generated sample is drawn from the estimated distribution of a few-shot class.  We evaluate this method on the Hematopoiesis dataset.  By simply eliminating samples based on thresholding our proposed GN scores, the few-shot  classification  performance  is  improved by 5% and 2% in five shot and one shot respectively, compared to the model trained on all generated images. 


The GN scores represent the similarity distances from the generated samples to their classes, based on the assumption that each class is a Gaussian distribution.  However, this assumption might be strict in many scenarios since the real distributions of data can be arbitrarily complex.  Thus in my second proposed method, I aim to learn such similarity distances directly from data via metric learning. I propose to train a deep-network to regress the similarity distance between a pair of samples.  This network is trained using both the class-level  visual  similarity  information  and  the  class  labels.   This method improves the 1-shot and 5-shot classification performances by 0.5% and 1% respectively, compared to GN.