← Search

Dinuka Sahabandu

2 accepted papers

2024

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

EMNLP 2024main

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to train or fine-tune these LLMs is often undisclosed, allowing…

2023

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

NeurIPS 2023poster

Federated learning (FL) provides a distributed training paradigm where multiple clients can jointly train a global model without sharing their local data. However, recent studies have shown that FL offers an additional surface for backdoor attacks. For instance, an attacker can compromise a subset o…