7 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…
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…
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…
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…
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…