341 citations · 1.6k across the 113 of their papers we have counts for
23 papers · 1 filter
ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity
Haoran Wang, Matthew Lau, Alec Helbling +7
Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches that cause them to miss objects…
ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
Mansi Phute, Alexander Greenhalgh, Matthew Hull +8
Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and…
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Alec Helbling, Tuna Han Salih Meral, Ben Hoover +2
Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel metho…
Effective Guidance for Model Attention with Simple Yes-no Annotations
Seongmin Lee, Ali Payani, Duen Horng Chau
Modern deep learning models often make predictions by focusing on irrelevant areas, leading to biased performance and limited generalization. Existing methods aimed at rectifying m…
Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors
Anisha Pal, Julia Kruk, Mansi Phute +4
Text-to-image diffusion models have impactful applications in art, design, and entertainment, yet these technologies also pose significant risks by enabling the creation and dissem…
UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining
ShengYun Peng, Aishwarya Chakravarthy, Seongmin Lee +3
Tables convey factual and quantitative data with implicit conventions created by humans that are often challenging for machines to parse. Prior work on table recognition (TR) has m…
Self-Supervised Pre-Training for Table Structure Recognition Transformer
ShengYun Peng, Seongmin Lee, Xiaojing Wang +2
Table structure recognition (TSR) aims to convert tabular images into a machine-readable format. Although hybrid convolutional neural network (CNN)-transformer architecture is wide…
High-Performance Transformers for Table Structure Recognition Need Early Convolutions
ShengYun Peng, Seongmin Lee, Xiaojing Wang +2
Table structure recognition (TSR) aims to convert tabular images into a machine-readable format, where a visual encoder extracts image features and a textual decoder generates tabl…
ObjectComposer: Consistent Generation of Multiple Objects Without Fine-tuning
Alec Helbling, Evan Montoya, Duen Horng Chau
Recent text-to-image generative models can generate high-fidelity images from text prompts. However, these models struggle to consistently generate the same objects in different co…
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
ShengYun Peng, Weilin Xu, Cory Cornelius +6
Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a sui…
RobArch: Designing Robust Architectures against Adversarial Attacks
ShengYun Peng, Weilin Xu, Cory Cornelius +4
Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs). However, compared to the large body of research in optimizing the a…
DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models
Zijie J. Wang, Evan Montoya, David Munechika +3
With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details re…
VisCUIT: Visual Auditor for Bias in CNN Image Classifier
Seongmin Lee, Zijie J. Wang, Judy Hoffman +1
CNN image classifiers are widely used, thanks to their efficiency and accuracy. However, they can suffer from biases that impede their practical applications. Most existing bias in…
SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning
Nilaksh Das, Sheng-Yun Peng, Duen Horng Chau
Person tracking using computer vision techniques has wide ranging applications such as autonomous driving, home security and sports analytics. However, the growing threat of advers…
NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks
Haekyu Park, Nilaksh Das, Rahul Duggal +4
Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are coll…
SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models
Haekyu Park, Zijie J. Wang, Nilaksh Das +4
Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. How…
UnMask: Adversarial Detection and Defense Through Robust Feature Alignment
Scott Freitas, Shang-Tse Chen, Zijie J. Wang +1
Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has dem…
Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA
Cory Cornelius, Shang-Tse Chen, Jason Martin +1
In this talk we describe our content-preserving attack on object detectors, ShapeShifter, and demonstrate how to evaluate this threat in realistic scenarios. We describe how we use…
GOGGLES: Automatic Image Labeling with Affinity Coding
Nilaksh Das, Sanya Chaba, Renzhi Wu +3
Generating large labeled training data is becoming the biggest bottleneck in building and deploying supervised machine learning models. Recently, the data programming paradigm has…
Interactive Classification for Deep Learning Interpretation
Ángel Alexander Cabrera, Fred Hohman, Jason Lin +1
We present an interactive system enabling users to manipulate images to explore the robustness and sensitivity of deep learning image classifiers. Using modern web technologies to…
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector
Shang-Tse Chen, Cory Cornelius, Jason Martin +1
Given the ability to directly manipulate image pixels in the digital input space, an adversary can easily generate imperceptible perturbations to fool a Deep Neural Network (DNN) i…
Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen +5
The rapidly growing body of research in adversarial machine learning has demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarially generated images. This…
Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen +4
Deep neural networks (DNNs) have achieved great success in solving a variety of machine learning (ML) problems, especially in the domain of image recognition. However, recent resea…