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:

Photorealistic editing of human facial expressions and head articulations remains a long-standing topic in the computer graphics and computer vision community. Methods enabling such control have great potential in AR/VR applications where a 3D immersive experience is valuable, especially when this control extends to novel views of the scene in which the human subject appears. Traditionally, 3D Morphable Face Models (3DMMs) have been used to control the facial expressions and head pose of a human head. However, the PCA-based shape and expression spaces of 3DMMs lack the expressivity. They cannot model essential elements of the human head such as hair, skin details, and accessories such as glasses that are paramount for realistic reanimation. In this thesis, we present a set of methods that enables facial reanimation, starting from editing expressions in still face images to creating fully controllable neural 3D portraits with control over facial expressions, head pose, and viewing direction of the scene using only casually captured monocular videos from a smartphone to finally achieving studio-like quality from the said monocular captures.
First, we propose a method for editing facial expressions in near-frontal facial images through the unsupervised disentangling of expression-induced deformations and texture changes. Next, we extend facial expression editing to human subjects in 3D scenes. We represent the scene and the subject in it using a semantically guided neural field. This enables control over the subject's facial expressions and the viewing direction of the scene they're in. We then present a method that learns, in an unsupervised manner, to deform static 3D neural fields using facial expression and head-pose dependent deformations, enabling control over facial expressions and head pose of the subject along with the viewing direction of the 3D scene they're in. Next, we propose a method that makes the learning of the aforementioned deformation field robust to strong illumination effects, which adversely impact the registration of the deformation. We then propose an extension of this unsupervised deformation model to 3D Gaussian splatting by constraining it using a 3D morphable model, resulting in a rendering speed of 18 FPS--a 100x speed improvement over prior work. Finally, we propose a method that bridges the quality gap between 3D portraits created using in-the-wild monocular data and multi-view studio capture data. We accomplish this using a two-stage method. First, we train a StyleGAN to relight and inpaint in-the-wild face texture maps (with strong illumination effects and incompletely captured regions). Next, we both reconstruct and generate identity-specific facial details that may be poorly captured in the in-the-wild captures. Once trained, we can generate studio-like complete avatars from monocular phone captures.

Speaker: Shahrukh Athar

Zoom Link:
https://stonybrook.zoom.us/j/94228500743?pwd=RqOBgG6tbJkKaFBlWFwBkYFX0VRovV.1

Meeting ID: 94228500743
Passcode: 661599

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. 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.

We meet every other Tuesday at noon in CDSD's Training Room (building 725, room 2-124) 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.

In addition to our speaker, we will have a number of CDS staff in attendance with expertise in AI methods and applications including image analysis, foundation models development, and inverse problem solving.

AI-Driven Physics-Informed Phase Retrieval from a Single X-ray

Abstract: X-ray phase-contrast imaging enables the visualization of weakly absorbing or low-contrast structures and plays an important role in materials, biological, and energy research. Conventional X-ray holography and phase-retrieval techniques typically require multiple intensity measurements acquired at different propagation distances to recover phase information, increasing acquisition time, radiation dose, and experimental complexity. In this work, we present an AI-driven, physics-informed approach for phase retrieval using only a single X-ray intensity measurement. The method adapted a generative neural network as an inverse reconstruction engine, with physical models of X-ray wave propagation embedded directly into the optimization process. This allows phase and absorption information to be recovered from a single hologram without relying on paired, unpaired, or simulated training datasets. By combining physical constraints with self-supervised AI reconstruction, the approach achieves stable and quantitative results across a wide range of imaging conditions. The results demonstrate how physics-informed AI can reduce experimental requirements and enable data-efficient, automated phase retrieval for next-generation X-ray imaging workflows.

Biography: Xiaogang Yang is a computational scientist in the Data Analysis & Workflow Integration group at NSLS-II, focusing on AI development for X-ray imaging, data analysis, and automated workflows. He earned his PhD from Delft University of Technology, completed his postdoctoral research at Argonne National Laboratory, and previously held a tenured position at PETRA III (DESY).

Location: CDS, Bldg. 725, Training Room

Join ZoomGov Meeting: https://bnl.zoomgov.com/j/1604383624?pwd=ffQ5cUPNxTI7nzClKQO6cnsNbhF9Vf.1

Meeting ID: 160 438 3624
Passcode: 558449

Please Note: Due to a funding shortfall, we are for the time being no longer able to provide pizza and sodas for these events. We will have coffee though, and all are of course welcome to bring their lunch.

Postmortem Program Analysis from a Conventional Program Analysis Method to an AI-assisted Approach

Abstract: Despite the best efforts of developers, software inevitably contains flaws that may be leveraged as security vulnerabilities. Modern operating systems integrate various security mechanisms to prevent software faults from being exploited. To bypass these defenses and hijack program execution, an attacker needs to constantly mutate an exploit and make many attempts. While in their attempts, the exploit triggers a security vulnerability and makes the running process abnormally terminate.

After a program has crashed and abnormally terminated, it typically leaves behind a snapshot of its crashing state in the form of a core dump. While a core dump carries a large amount of information, which has long been used for software debugging, it barely serves as informative debugging aids in locating software faults, particularly memory corruption vulnerabilities. As such, previous research mainly seeks fully reproducible execution tracing to identify software vulnerabilities in crashes. However, such techniques are usually impractical for complex programs. Even for simple programs, the overhead of fully reproducible tracing may only be acceptable at the time of in-house testing.

In this talk, I will discuss how we tackle this issue by bridging program analysis with artificial intelligence (AI). More specifically, I will first talk about the history of postmortem program analysis, characterizing and disclosing their limitations. Second, I will introduce how we design a new reverse-execution approach for postmortem program analysis. Third, I will discuss how we integrate AI into our reverse-execution method to escalate its analysis efficiency and accuracy. Last but not least, as part of this talk, I will demonstrate the effectiveness of this AI-assisted postmortem program analysis framework by using massive amounts of real-world programs.

Bio: Dr. Xinyu Xing is an Assistant Professor at Pennsylvania State University. His research interests include exploring, designing and developing new program analysis and AI techniques to automate vulnerability discovery, failure reproduction, vulnerability diagnosis (and triage), exploit and security patch generation. His past research has been featured by many mainstream media and received the best paper awards from ACM CCS and ACSAC. Going beyond academic research, he also actively participates and hosts many world-class cybersecurity competitions (such as HITB and XCTF). As the founder of JD-OMEGA, his team has been selected for DEFCON/GeekPwn AI challenge grand final at Las Vegas. Currently, his research is mainly supported by NSF, ONR, NSA and industry partners.
Abstract: Retrieval-augmented generation (RAG) systems empower large language models (LLMs) to access external knowledge during inference. Recent advances have enabled LLMs to act as search agents via reinforcement learning (RL), improving information acquisition through multi-turn interactions with retrieval engines. However, existing approaches either optimize retrieval using search-only metrics (e.g., NDCG) that ignore downstream utility or fine-tune the entire LLM to jointly reason and retrieve--entangling retrieval with generation and limiting the real search utility and compatibility with frozen or proprietary models. In this work, we propose s3, a lightweight, model-agnostic framework that decouples the searcher from the generator and trains the searcher using a Gain Beyond RAG reward: the improvement in generation accuracy over naïve RAG. s3 requires only 2.4k training samples to outperform baselines trained on over 70 × more data, consistently delivering stronger downstream performance across six general QA and five medical QA benchmarks.

Speaker: Peter Zeng

Location: CS2311

An interactive session to discover how to create ALT text tags from images and create high-impact visuals, from identification to communicating ideas with images.

Discover how to use AI to create ALT text from images as well as identify objects in your environment, and build relatable visuals for high-impact presentations. Images communicate ideas as a way to understand concepts. AI-generated images have helped allow anyone to create these.

In this session, you will

  1. Creating image ALT Tags
  2. Transform ideas into images that are visually appealing
  3. Identify objects from visuals

Register here.
Abstract: Visual generation is a fundamental problem in computer vision and graphics, with applications ranging from 3D capture to content creation and image/video synthesis. Despite rapid progress in neural rendering and generative models, efficiency remains a key obstacle in practice: high-quality 3D reconstruction often depends on dense multi-view supervision; scalable 3D synthesis faces heavy optimization, training, and rendering costs; and modern image/video generators incur substantial computation as token grids grow with spatial resolution and temporal length.
This thesis targets efficient visual world modeling by improving sample efficiency in 3D reconstruction, representation efficiency in 3D generation, and computational efficiency in image/video synthesis. First, we improve sample efficiency for neural implicit surface reconstruction under sparse views by integrating multi-view stereo probability volumes as a geometric regularizer, enabling high-quality reconstruction from as few as three input images. Next, we introduce an explicit 3D representation for 3D generation, built from multi-view depth and RGB predictions with 3D Gaussian features, which enables the use of 2D generative priors while enforcing multi-view consistency via epipolar attention. We then address the computational bottleneck of image and video synthesis with importance-based token merging, using importance signals available during generation to preserve critical information while merging redundant tokens. Finally, we propose efficient mixed-resolution diffusion transformers via cross-resolution phase-aligned attention, aiming to improve attention stability under mixed token grids and support high-fidelity mixed-resolution generation.

Speaker: Haoyu Wu

Location: NCS120

Discover how Google Gemini can help you draft lesson plans, generate discussion questions, design activities, and create course materials in a fraction of the time.

You have a workshop to plan, need an engaging activity, and a stack of content to create, but not enough time? Google Gemini, available through your SBU Google account, can help you brainstorm, draft, and refine lesson plans, learning objectives, discussion prompts, rubrics, and more. This session is designed for anyone who is interested in using Gemini to help generate learning activities.

In this session, you will:

  1. Access Google Gemini using your SBU Google account
  2. Write effective prompts for lesson planning and content creation
  3. Generate and refine learning objectives, discussion questions, and activities
  4. Create or improve course materials such as rubrics, instructions, and assessment ideas
  5. Apply best practices for reviewing and adapting AI-generated content

Register here.