Abstract: Large Language Models (LLMs) have transitioned from standalone prediction interfaces into integrated systems that incorporate content protection, external knowledge retrieval, and multi-step reasoning. While these functional layers expand model capabilities, they also introduce complex, inter-component dependencies that create novel and systemic security risks. This research provides a systematic deconstruction of the structural vulnerabilities emerging across these functional layers.

In this proposal, we evaluate the security boundaries of LLM systems through three pivotal dimensions:
The Content Layer: We present Watermark under Fire, revealing the inherent fragility of content-based tracing mechanisms under adaptive perturbations and highlighting the limitations of surface-level safety measures.
The Retrieval Layer: We introduce GraphRAG under Fire to examine the security of topology-aware knowledge integration. We reveal how graph-based indexing can be exploited as a structural lever for high-success poisoning attacks.
The Reasoning Layer: We detail AutoRAN, the first framework demonstrating the hijacking of internal safety reasoning in Large Reasoning Models (LRMs). This work proves that the transparency of the reasoning process itself creates a critical and exploitable attack surface.

Collectively, these studies demonstrate a systemic failure of add-on safety mechanisms in securing the broader LLM ecosystem. By identifying recurring patterns of exploitation across different system layers, this research provides the necessary foundation for transitioning from reactive patching to a more unified and architecturally-grounded approach to AI trustworthiness.

Speaker: Jiacheng Liang

Zoom: https://stonybrook.zoom.us/j/6669990420?pwd=dkY0eEw5YXpPSWo3RUE4OE1oVW90UT09&omn=97367037382
Meeting ID: 666 999 0420
Passcode: 075299
Abstract:

Capturing the spatio-temporal (4D) dynamics of humans has been a long standing research problem in computer vision and graphics. Synthesizing photorealistic human avatars has broad applications, ranging from immersive telepresence in AR/VR and the movie industry, to enriching the education and healthcare systems. Earlier approaches relied on hand-engineered models that use a small amount of data from one or more subjects. With the advent of neural networks, training on large datasets enhanced the output visual quality. Currently, the combination of neural networks with graphics techniques has achieved natural-looking human animation. However, most approaches are identity-specific, trained only on a single identity, and use only one modality.

In this thesis, we address the problem of learning neural representations of humans in a holistic way. Given that the video data in the real world include multiple modalities (audio and video) and multiple identities, we develop multi-modal and multi-identity representations. First, we propose to reconstruct the 4D face geometry of humans by leveraging both audio and video information. In this way, the network produces accurate lip shapes and is robust to cases when either modality is insufficient. Next, we introduce a NeRF-based representation for audio-driven human face animation that achieves high-quality lip synchronization for cinematic content. Since humans communicate with their full body, combining body pose, hand gestures, and facial expressions, we extend our network to capture the full-body human motion for multiple identities simultaneously. In order to better disentangle identity and non-identity specific information, we subsequently study non-linear interactions between latent factors of variation, and propose a specific multiplicative module. In this way, we learn a multi-identity NeRF that robustly animates human faces under novel expressions and achieves a significant decrease in the total training time. Similarly, we propose a multi-identity gaussian splatting representation for human bodies, by constructing a high-order tensor. Assuming a low-rank structure, we learn a tensor decomposition that leads to a significant decrease in the total number of learnable parameters, as well as to a robust animation under novel poses. In the future, we propose to jointly synthesize audio and visual outputs from just text input. Given the recent rise of large language models, coupling text with natural-looking avatars can enhance the overall interaction between a human and an AI system.

Speaker: Aggelina Chatziagapi

Where: NCS, Room 220

Zoom link: https://stonybrook.zoom.us/j/98775312249?pwd=uORNAnSdcssrPZdqOsqaMAF5aLcRD9.1
ID: 98775312249
Passcode: 505777
The North East AI Agents Day Organizing Committee invites you to '2026 AI Agents Day.'

The goal of this workshop is to offer a comprehensive overview of AI agents, bring ML, Systems, and HCI research communities together to share progress, discuss common problems and evaluation setups, and identify opportunities for collaboration. We aim to bring together attendees from diverse disciplines to foster interdisciplinary collaboration and discuss open research questions.

Location: Jane Street Offices, New York

Register here.

The Provost's Spotlight Talks feature eminent visitors to the university as well as Stony Brook faculty members who have recently been recognized for outstanding contributions in their field.

Transmedia artist Stephanie Dinkins, Kusama endowed chair in art in the College of Arts and Sciences at Stony Brook University, brings her expertise in AI to the next Spotlight Talk with The Stories We Encode: AI, Love and the Future of Algorithmic Care on Tuesday, October 22, at 3:30 pm in the Charles B. Wang Center Theatre.

Working at the intersection of emerging technologies and social collaboration, Dinkins was named a 2023 TIME 100 Most Influential People in AI. She was recognized for her work with Not the Only One, an ongoing project in which she trained an AI on three generations of Black women to give it cultural roots, a deep history, and a perspective that existing systems do not offer.

The event is free and open to the public, and the discussion will be followed by a reception in the Wang Theatre lobby, hosted by the College of Arts and Sciences for new and promoted faculty.


About the Talk

AI's impact on society necessitates addressing longstanding human rights issues and prejudices. To ensure AI benefits humanity, we must confront institutional biases, rethink our relationship with other beings and emerging technologies, and reconcile ideals with actual power structures. This involves recognizing systemic inequalities, redefining human identity, and equitably distributing resources. AI, if developed and used ethically, offers an opportunity to reimagine a more equitable world for all inhabitants.

You are cordially invited to attend the biweekly Brookhaven AI Mixer (BAM). BAM includes one short talk on AI research happening at BNL, followed by an open mixer over coffee and snacks for everyone to network and discuss all things AI. The first half hour will consist of presentations that will be available via ZOOM, and the second half hour will be for in person only networking.

Join us every other Tuesday at noon in CDSD's Training Room (building 725, 2nd floor) to learn about interesting AI methods and applications, engage with potential collaborators, prepare for pending FASST funding calls, and build a community of AI for Science at BNL.

#1 How to train your Scientific Chatbot by Alexandr Prozorov, Post-Doctoral Research Associate


Abstract: RHIC is closing its 25-year run with ~1 EB of data and decades of hard-won know-how that risk drifting into obscurity. The RHIC Data & Analysis Preservation Plan (DAPP) pilots an AI assistant that lets physicists talk to RHIC in natural language--searching internal notes, code, workflows, and docs, and pointing to runnable, containerized analyses. Built on Retrieval-Augmented Generation(RAG) with a Model Context Protocol orchestration layer, the system indexes heterogeneous, experiment-specific content and enforces role-aware access
for public vs. collaboration-restricted materials. Takeaway: domain-adapted AI can turn a legacy exabyte into reproducible answers, training assets, and new discovery paths.

Biography: Alexandr Prozorov is a postdoc from Czech Technical University in Prague working in STAR experiment. Fascinated by AI

#2 Quantum AI: Atoms, Cavities and Learning by Raman Kumar, Post-Doctoral Research Associate, Instrumentation Department

Abstract: The Instrumentation Department (IO) in the Discovery Technologies directorate at BNL is engaged in exploring various aspects of quantum systems research. One of the main goals of our group's effort is in developing neutral atom-cavity array platforms for remote entanglement generation and distributed quantum processing. This platform promises to herald truly scalable quantum computing systems and open new paradigms for networking and sensing. In this talk, I will explain our group's research and the role AI is playing in unlocking new insights with two examples. The first application of AI is in fabrication process prediction of micro-cavity structures. The second application revolves around role of AI in quantum error detection and correction in modern quantum computing systems.

Biography: Dr. Raman Kumar is a postdoctoral research associate in the IO department at BNL working with Dr./Prof. Sebastian Will (Columbia U.). Kumar obtained his Ph.D. degree in Electrical and Computer Engineering from the University of Illinois Urbana-Champaign. Prior to joining BNL in Nov 2024, Kumar worked as a postdoc at the City College in New York working on topological photonic quantum sensing using NV centers in diamond. Kumar and Will combined have an extremely wide moat and expertise in a variety of different areas which include Ultra cold atoms and molecules, quantum optics, quantum condensed matter, nanofabrication, semiconductor devices and advanced electromagnetics. Their areas of research interest include scalable quantum computing, communications and sensing, all enabled by AI.

Location: CDS, Bldg. 725, Training Room

Join ZoomGov Meeting https://bnl.zoomgov.com/j/1607892208?pwd=MSjxN5btSeToZsQMwEQzCCbBo5h58V.1

Meeting ID: 160 789 2208
Passcode: 753871

University Libraries Presents: The Library AI Club is a welcoming space for students, faculty, and staff to explore AI in a supportive, low-pressure environment. Meeting every two weeks, the club features discussions, collaborative projects, guest speakers, and hands-on experiments. Join us to learn, share ideas, and engage with AI responsibly and creatively. We'd love to see you at an upcoming meeting! Location: Melville Library, Scholarly Communication Seminar Room

AI for Business: An Executive Workshop

A one-day workshop jointly presented by the Stony Brook University AI Innovation Institute (AI3) and the College of Business


November 20, 2026, 8:30 AM - 5:30 PM
The SUNY Global Center, 116 East 55th Street, New York, NY 10022

Decide where AI creates value for your organization, then build a 90-day plan to support it.


  • A working session for senior leaders.

  • You will not be taught to code, and you will not sit through a technology briefing.

  • You will leave with:
    - A shortlist of AI opportunities specific to your organization
    - An honest assessment of what you would need to deliver them
    - A written 90-day plan with named owners and success measures


Seats are limited to 30 participants

Read more and register

You are cordially invited to attend the biweekly Brookhaven AI Mixer (BAM). BAM includes one short talk on AI research happening at BNL, followed by an open mixer over coffee and snacks for everyone to network and discuss all things AI. The first half hour will consist of presentations that will be available via ZOOM, and the second half hour will be for in person only networking.

Join us every other Tuesday at noon in CDSD's Training Room (building 725, 2nd floor) to learn about interesting AI methods and applications, engage with potential collaborators, prepare for pending FASST funding calls, and build a community of AI for Science at BNL.

HPCortex - a new, general-purpose machine learning library for HPC

Abstract: I will introduce HPCortex, a lightweight, C++, MPI-native machine-learning library for heterogeneous HPC systems. It implements many common architecture patterns including transformers, graph neural networks, and convolutional networks, and delivers performance portability across NVIDIA, AMD, and Intel GPUs while depending only on MPI and standard compiler/BLAS stacks. I will illustrate its capabilities via a surrogate model for the RHIC AGS Booster digital twin, a simple GNN for a coupled spring system, and a compact language model, then outline the roadmap.

Biography: Christopher is a research scientist and head of the Scientific Computing Applications Group in the Computational Science Department at Brookhaven National Laboratory. Previously he was an assistant staff scientist in the Physics Dept. at Columbia University, and held physics postdoctoral research positions at both Brookhaven and Columbia. He earned his Ph.D in Theoretical Physics from the University of Edinburgh, UK.
His scientific background is in lattice QCD and high performance computing, but since joining Brookhaven in 2020 his research interests have expanded to include machine learning, applied mathematics and performance analysis, with a particular emphasis on building tools to support scientific research on HPC systems.

Location: CDS, Bldg. 725, Training Room

Join ZoomGov Meeting: https://bnl.zoomgov.com/j/1604143373?pwd=hHT2yaIjahBIQ6tieURFqs8Pwex9gU.1

Meeting ID: 160 414 3373
Passcode: 277410