Karthik Nandakumar

10

Papers

97

Total Citations

Papers (10)

DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models

STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models

Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline

Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models

CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search

Evading Forensic Classifiers With Attribute-Conditioned Adversarial Faces

FLIP: Cross-domain Face Anti-spoofing with Language Guidance

CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss

A Framework for Double-Blind Federated Adaptation of Foundation Models

Byzantine-Tolerant Methods for Distributed Variational Inequalities