43 citations · 91 across the 13 of their papers we have counts for
13 papers
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
Alexandra Souly, Javier Rando, Ed Chapman +10
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…
From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs
Alsharif Abuadbba, Chris Hicks, Kristen Moore +4
Large Language Models (LLMs) are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simula…
One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image
Ezzeldin Shereen, Dan Ristea, Shae McFadden +3
Retrieval-augmented generation (RAG) is instrumental for inhibiting hallucinations in large language models (LLMs) through the use of a factual knowledge base (KB). Although PDF do…
Generalized Multivariate Polynomial Codes for Distributed Matrix-Matrix Multiplication
Jesús Gómez-Vilardebó, Burak Hasırcıoğlu, Deniz Gündüz
Supporting multiple partial computations efficiently at each of the workers is a keystone in distributed coded computing in order to speed up computations and to fully exploit the…
Private Collaborative Edge Inference via Over-the-Air Computation
Selim F. Yilmaz, Burak Hasircioglu, Li Qiao +1
We consider collaborative inference at the wireless edge, where each client's model is trained independently on its local dataset. Clients are queried in parallel to make an accura…
Communication Efficient Private Federated Learning Using Dithering
Burak Hasircioglu, Deniz Gunduz
The task of preserving privacy while ensuring efficient communication is a fundamental challenge in federated learning. In this work, we tackle this challenge in the trusted aggreg…
Privacy Amplification via Random Participation in Federated Learning
Burak Hasircioglu, Deniz Gunduz
Running a randomized algorithm on a subsampled dataset instead of the entire dataset amplifies differential privacy guarantees. In this work, in a federated setting, we consider ra…
Over-the-Air Ensemble Inference with Model Privacy
Selim F. Yilmaz, Burak Hasircioglu, Deniz Gunduz
We consider distributed inference at the wireless edge, where multiple clients with an ensemble of models, each trained independently on a local dataset, are queried in parallel to…
Bivariate Polynomial Codes for Secure Distributed Matrix Multiplication
Burak Hasircioglu, Jesus Gomez-Vilardebo, Deniz Gunduz
We consider the problem of secure distributed matrix multiplication (SDMM). Coded computation has been shown to be an effective solution in distributed matrix multiplication, both…
Speeding Up Private Distributed Matrix Multiplication via Bivariate Polynomial Codes
Burak Hasircioglu, Jesus Gomez-Vilardebo, Deniz Gunduz
We consider the problem of private distributed matrix multiplication under limited resources. Coded computation has been shown to be an effective solution in distributed matrix mul…
Dopamine: Differentially Private Federated Learning on Medical Data
Mohammad Malekzadeh, Burak Hasircioglu, Nitish Mital +3
While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients' privacy is a barrier against using such data to train deep neural networks (…
Private Wireless Federated Learning with Anonymous Over-the-Air Computation
Burak Hasircioglu, Deniz Gunduz
In conventional federated learning (FL), differential privacy (DP) guarantees can be obtained by injecting additional noise to local model updates before transmitting to the parame…
Bivariate Polynomial Coding for Efficient Distributed Matrix Multiplication
Burak Hasircioglu, Jesus Gomez-Vilardebo, Deniz Gunduz
Coded computing is an effective technique to mitigate "stragglers" in large-scale and distributed matrix multiplication. In particular, univariate polynomial codes have been shown…