Matthew Salzano (Stony Brook), AI and DEIA: Getting at the Roots

Link to the talk (no pre-registration required this time): https://stonybrook.zoom.us/j/96209347479?pwd=Cs8fEfFdbXrGTC5cQgyHRb8Msh5vp8.1Meeting ID: 962 0934 7479 Passcode: 272489

Abstract: Conversations about AI and DEIA (Diversity, Equity, Inclusion, and Access) often unwittingly assume that social problems can and should have technical fixes. Left unaddressed, scholars, advocates, and technologists inevitably miss important consequences in our proposed solutions, and focus on surface-level problems rather than addressing the root causes of inequity. Drawing from scholarship in communication, rhetoric, and critical digital studies, this talk explains how we are often trimming branches when we need to pull out roots -- and introduces new terms and questions that can help reorient our conversations about AI and DEIA.

Speaker Bio: Matthew Salzano, Ph.D., is a communication scholar researching new media technologies, user practices, and cultural trends that threaten to limit possibilities for diverse engagement in public argument, debate, and protest. His scholarship has appeared in journals like The Quarterly Journal of Speech, Critical Studies in Media Communication, and Women's Studies in Communication, and his research on DEIA, AI, and advocacy communications has been funded by the Waterhouse Family Institute at Villanova University. He is currently an Inclusion, Diversity, Equity, and Access fellow in Ethical AI at Stony Brook University's School of Communication and Journalism and Alan Alda Center for Communicating Science.

Abstract: Recent studies have highlighted the vulnerability of Natural Language Processing (NLP) and Vision-Language Models (VLMs) to backdoor attacks, posing significant security risks. Understanding these attack strategies is crucial for assessing model robustness and developing effective defenses. This thesis proposal aims to investigate the vulnerability of language and vision-language models, analyze abnormal behaviors in backdoor-attacked models, and develop defense methods to enhance safety of modern machine learning models at deployment.


We investigate the internal mechanisms of backdoored NLP models, identifying a distinct attention focus drifting phenomenon, where trigger tokens hijack attention regardless of the input context. Through comprehensive qualitative and quantitative analysis, we provide insights into the underlying mechanisms that enable backdoor attacks. Building on these insights, we propose detection methods to differentiate backdoored models from clean ones, through inspecting both the attention distribution and the model predictions. To better understand the vulnerability, we develop advanced backdoor attack strategies targeting language models in classification tasks. For BERT variants, we introduce Trojan Attention Loss (TAL), a novel method that directly manipulates attention patterns to enhance backdoor effectiveness, ensuring stealth and robustness. Vision-Language Models have demonstrated strong performance in recent years. Yet their vulnerability is largely underexplored. We investigate advanced backdoor attack strategies on Vision-Language Models, focusing on image-to-text generation tasks. We demonstrate how backdoors can be embedded in complex multimodal tasks while maintaining semantic integrity under poisoned inputs. Additionally, we propose innovative techniques for injecting backdoors without requiring access to the original training data, expanding the feasibility of real-world attacks.

This proposal provides novel insights into the internal mechanisms of backdoored models, propose effective detection strategies, and develop advanced attack techniques that expose critical vulnerabilities. These findings underscore the urgent need for robust security measures to defend against emerging backdoor threats in deep learning models. The results have been published in top venues including ICLR, ECCV, NAACL, EMNLP, etc.

Speaker: Weimin Lyu


Zoom link: https://stonybrook.zoom.us/j/99880605139?pwd=cfWbRG6n9v3GXEa7OqvXa5cOp5eLBv.1
Meeting ID: 998 8060 5139
Passcode: 843302
The coach who led Team USA to four Math Olympiad gold medals shares his blueprint for staying irreplaceable in an AI-driven world.

As artificial intelligence transforms our world, what skills will remain uniquely human? How can we prepare for careers in an automated future?

Join Carnegie Mellon mathematics professor Po-Shen Loh for insights on navigating the AI revolution by embracing our humanity.

Dr. Loh brings a distinctive perspective shaped by his dual expertise: serving as national coach of the USA Mathematical Olympiad team (which has won four gold medals under his leadership) and developing innovative solutions for real-world challenges from pandemic response to educational technology.

Through his nationwide speaking tour that reached 250 audiences across 100 cities, he has refined a practical framework for thriving alongside AI.

In this presentation, Dr. Loh will explore how creative problem-solving, judgment, and communication become more valuable as automation grows -- and how students and professionals can build those strengths now.

The session includes real-world examples, guidance for education and careers, and a Q&A.

Speaker: Po-Shen Loh is a social entrepreneur and inventor, working across the spectrum of mathematics, education, and healthcare.

A math professor at Carnegie Mellon University, he also served a decade-long term as the national coach of the USA International Mathematical Olympiad (IMO) team, taking the team to gold on numerous occasions.

He has pioneered numerous innovations and has been featured in or co-created YouTube videos with more than 25 million views.

Location: Wang Center Theater

The series is offered by Stony Brook University's Institute for Creative Problem Solving in collaboration with the National Museum of Mathematics (MoMath) and Brookhaven National Laboratory.

The event is free but space is limited. Please register to reserve your space.

Over the past decade, Artificial Intelligence (AI) has made stunning advances, from mastering language to solving the structure of proteins. These breakthroughs arise from more than forty years of work in neural networks, where ideas from neuroscience have inspired solutions in AI. In this lecture, Anthony Zador, MD, PhD, will explore how reverse engineering the brain's computations has driven progress in both fields, and how this back-and-forth between neuroscience and AI is set to grow even stronger -- with brain-inspired designs driving new AI advances while AI tools transform our understanding of how the brain works.

Speaker:
Dr. Zador works at the intersection of neuroscience and artificial intelligence. He is the Alle Davis Harris Professor of Biology at Cold Spring Harbor Laboratory, where he served as Chair of Neuroscience. He was named one of Foreign Policy's 100 Leading Global Thinkers and is a recipient of the Brain Research Foundation Fellowship, the Gill Symposium Transformative Investigator Award, and the Allen Distinguished Investigator Award.

Watch online at stonybrook.edu/live
Join Zoom Meeting
https://stonybrook.zoom.us/j/98079526509?pwd=Wkt5eURhVDN5VE56TUloS2h5V1Jodz09

Meeting ID: 980 7952 6509
Passcode: 949941



Abstract Over the last decade, artificial neural networks have undergone a revolution, catalyzed by better
supervised learning algorithms. However, in stark contrast to young animals (including humans), training such
networks requires enormous numbers of labeled examples, leading to the belief that animals must rely instead
mainly on unsupervised learning. The reason is that most animal behavior is not the result of clever learning
algorithms--supervised or unsupervised-- but is encoded in the genome. Specifically, animals are born with
highly structured brain connectivity, which enables them to learn very rapidly. Because the wiring diagram is
far too complex to be specified explicitly in the genome, it must be compressed through a genomic
bottleneck. I will describe results showing how the genomic bottleneck algorithm can lead to dramatic
compression of networks and better generalization, particularly for rapid transfer in supervised and
reinforcement learning.

Anthony Zador is professor of neuroscience at CSHL.
University Libraries Present: Qualitative data can be challenging to analyze and interpret effectively. In this workshop, SBU Libraries' Data Literacies Lead, Ahmad Pratama will show you how to extract meaningful insights from textual data, including understanding sentiment trends. Learn to explore qualitative data with Python using word clouds, basic natural language processing (NLP) techniques, and lexicon-based sentiment analysis with VADER.
https://stonybrook.zoom.us/meeting/register/k0r6mPYCRayk2AOGmyd0qw#/registration

This is Stony Brook's quantum moment. Join us for a spotlight on the core achievements and research excellence of faculty across the Colleges of Arts and Sciences (CAS), and Engineering and Applied Sciences (CEAS) - and their collaborative advancements in quantum science and technology. Learn about the real world impact of their enduring work, their leadership in translating foundational science into entrepreneurial opportunities, and their impetus for making connections to next generation innovation.

Presented by: Catherine Chen, Ph.D., Research Development Associate

Welcome remarks: President Andrea Goldsmith

Panel moderators: Dean David Wrobel, CAS, and Dean Andrew Singer, CEAS

Presentations and panel featuring our faculty:

  • Jennifer Cano, CAS, Physics and Astronomy

  • P. Scott Carney, CEAS, Mechanical Engineering

  • Hyeongrak Chuck Choi, CEAS, Electrical and Computer Engineering

  • Eden Figueroa, CAS, Physics and Astronomy

  • Humanshu Gupta, CEAS, Computer Science

  • Angela Kelly, CAS, Physics and Astronomy

Location: Theatre at the Charles B. Wang Center, Stony Brook University

Reserve your tickets by March 26!