5 papers
PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction
Prajas Wadekar, Venkata Sai Pranav Bachina, Kunal Bhosikar +2
3D Gaussian Splatting (3DGS) has recently enabled highly photorealistic 3D reconstruction from casually captured multi-view images. However, this accessibility raises a privacy con…
LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs
Himanshu Pal, Venkata Sai Pranav Bachina, Ankit Gangwal +1
Temporal Graph Neural Networks (TGNNs) are increasingly used in high-stakes domains, such as financial forecasting, recommendation systems, and fraud detection. However, their susc…
Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability
Mauro Conti, Ankit Gangwal, Aaryan Ajay Sharma
Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training data, into on…
KeTS: Kernel-based Trust Segmentation against Model Poisoning Attacks
Ankit Gangwal, Mauro Conti, Tommaso Pauselli
Federated Learning (FL) enables multiple users to collaboratively train a global model in a distributed manner without revealing their personal data. However, FL remains vulnerable…
GENIE: Watermarking Graph Neural Networks for Link Prediction
Venkata Sai Pranav Bachina, Ankit Gangwal, Aaryan Ajay Sharma +1
Graph Neural Networks (GNNs) have become invaluable intellectual property in graph-based machine learning. However, their vulnerability to model stealing attacks when deployed with…