181 citations · 505 across the 54 of their papers we have counts for
61 papers
FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
Sepehr Dehdashtian, Jacob H Seidman, Vishnu N Boddeti +1
Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD models requires developing data…
Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
Ramin Akbari, Milad Afshari, Vishnu Naresh Boddeti
Concept erasure aims to remove unwanted attributes, such as social or demographic factors, from learned representations, while preserving their task-relevant utility. While the goa…
PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors
Sepehr Dehdashtian, Mashrur M. Morshed, Jacob H. Seidman +2
Synthetic image detectors (SIDs) are a key defense against the risks posed by the growing realism of images from text-to-image (T2I) models. Red teaming improves SID's effectivenes…
Estimating Parameter Fields in Multi-Physics PDEs from Scarce Measurements
Xuyang Li, Mahdi Masmoudi, Rami Gharbi +2
Parameterized partial differential equations (PDEs) underpin the mathematical modeling of complex systems in diverse domains, including engineering, healthcare, and physics. A cent…
DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows
Mashrur M. Morshed, Vishnu Boddeti
Many real-world applications of flow-based generative models desire a diverse set of samples that cover multiple modes of the target distribution. However, the predominant approach…
CoInD: Enabling Logical Compositions in Diffusion Models
Sachit Gaudi, Gautam Sreekumar, Vishnu Boddeti
How can we learn generative models to sample data with arbitrary logical compositions of statistically independent attributes? The prevailing solution is to sample from distributio…
Compositional World Knowledge leads to High Utility Synthetic data
Sachit Gaudi, Gautam Sreekumar, Vishnu Boddeti
Machine learning systems struggle with robustness, under subpopulation shifts. This problem becomes especially pronounced in scenarios where only a subset of attribute combinations…
OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes
Sepehr Dehdashtian, Gautam Sreekumar, Vishnu Naresh Boddeti
Images generated by text-to-image (T2I) models often exhibit visual biases and stereotypes of concepts such as culture and profession. Existing quantitative measures of stereotypes…
Fairness and Bias Mitigation in Computer Vision: A Survey
Sepehr Dehdashtian, Ruozhen He, Yi Li +4
Computer vision systems have witnessed rapid progress over the past two decades due to multiple advances in the field. As these systems are increasingly being deployed in high-stak…
A Deep Learning Framework for Three Dimensional Shape Reconstruction from Phaseless Acoustic Scattering Far-field Data
Doga Dikbayir, Abdel Alsnayyan, Vishnu Naresh Boddeti +2
The inverse scattering problem is of critical importance in a number of fields, including medical imaging, sonar, sensing, non-destructive evaluation, and several others. The probl…
The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models
Abeba Birhane, Sepehr Dehdashtian, Vinay Uday Prabhu +1
Scale the model, scale the data, scale the GPU farms is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling a…
Enhancing Privacy in Face Analytics Using Fully Homomorphic Encryption
Bharat Yalavarthi, Arjun Ramesh Kaushik, Arun Ross +2
Modern face recognition systems utilize deep neural networks to extract salient features from a face. These features denote embeddings in latent space and are often stored as templ…
Utility-Fairness Trade-Offs and How to Find Them
Sepehr Dehdashtian, Bashir Sadeghi, Vishnu Naresh Boddeti
When building classification systems with demographic fairness considerations, there are two objectives to satisfy: 1) maximizing utility for the specific task and 2) ensuring fair…
Action Reimagined: Text-to-Pose Video Editing for Dynamic Human Actions
Lan Wang, Vishnu Boddeti, Sernam Lim
We introduce a novel text-to-pose video editing method, ReimaginedAct. While existing video editing tasks are limited to changes in attributes, backgrounds, and styles, our method…
FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
Sepehr Dehdashtian, Lan Wang, Vishnu Naresh Boddeti
Large pre-trained vision-language models such as CLIP provide compact and general-purpose representations of text and images that are demonstrably effective across multiple downstr…
Mechanics-Informed Autoencoder Enables Automated Detection and Localization of Unforeseen Structural Damage
Xuyang Li, Hamed Bolandi, Mahdi Masmoudi +3
Structural health monitoring (SHM) ensures the safety and longevity of structures like buildings and bridges. As the volume and scale of structures and the impact of their failure…
Into the LAIONs Den: Investigating Hate in Multimodal Datasets
Abeba Birhane, Vinay Prabhu, Sang Han +2
'Scale the model, scale the data, scale the compute' is the reigning sentiment in the world of generative AI today. While the impact of model scaling has been extensively studied,…
AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE
Wei Ao, Vishnu Naresh Boddeti
Secure inference of deep convolutional neural networks (CNNs) under RNS-CKKS involves polynomial approximation of unsupported non-linear activation functions. However, existing app…
Spurious Correlations and Where to Find Them
Gautam Sreekumar, Vishnu Naresh Boddeti
Spurious correlations occur when a model learns unreliable features from the data and are a well-known drawback of data-driven learning. Although there are several algorithms propo…
Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services
Zhichao Lu, Chuntao Ding, Shangguang Wang +3
Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interes…
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Chuntao Ding, Zhichao Lu, Shangguang Wang +2
Multi-task learning (MTL) seeks to learn a single model to accomplish multiple tasks by leveraging shared information among the tasks. Existing MTL models, however, have been known…
On the Biometric Capacity of Generative Face Models
Vishnu Naresh Boddeti, Gautam Sreekumar, Arun Ross
There has been tremendous progress in generating realistic faces with high fidelity over the past few years. Despite this progress, a crucial question remains unanswered: "Given a…
Discovering Adaptable Symbolic Algorithms from Scratch
Stephen Kelly, Daniel S. Park, Xingyou Song +8
Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero (ARZ), a method based…
On Hate Scaling Laws For Data-Swamps
Abeba Birhane, Vinay Prabhu, Sang Han +1
`Scale the model, scale the data, scale the GPU-farms' is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling…