15 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…
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…
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…
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…
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…