65 citations · 111 across the 15 of their papers we have counts for
15 papers
Rethinking Indirect Prompt Injection as a Test-Time Search Problem
Duong M. Nguyen, Joon Sik Kim, Blazej Manczak +1
We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this…
Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs
Blazej Manczak, Eric Lin, Francisco Eiras +2
Large language models (LLMs) are rapidly transitioning into medical clinical use, yet their reliability under realistic, multi-turn interactions remains poorly understood. Existing…
Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing
James O' Neill, Santhosh Subramanian, Eric Lin +1
The trend towards large language models (LLMs) for guardrailing against undesired behaviors is increasing and has shown promise for censoring user inputs. However, increased latenc…
Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
Francisco Eiras, Eliott Zemour, Eric Lin +1
Large Language Model (LLM) based judges form the underpinnings of key safety evaluation processes such as offline benchmarking, automated red-teaming, and online guardrailing. This…
PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing
Blazej Manczak, Eliott Zemour, Eric Lin +1
Deploying language models (LMs) necessitates outputs to be both high-quality and compliant with safety guidelines. Although Inference-Time Guardrails (ITG) offer solutions that shi…
Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection
Taehyeon Kim, Eric Lin, Junu Lee +2
Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with…
Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?
Albert Yu Sun, Eliott Zemour, Arushi Saxena +4
Machine learning practitioners often fine-tune generative pre-trained models like GPT-3 to improve model performance at specific tasks. Previous works, however, suggest that fine-t…
Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy
David Byrd, Vaikkunth Mugunthan, Antigoni Polychroniadou +1
Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted…
Gradient Masked Averaging for Federated Learning
Irene Tenison, Sai Aravind Sreeramadas, Vaikkunth Mugunthan +3
Federated learning (FL) is an emerging paradigm that permits a large number of clients with heterogeneous data to coordinate learning of a unified global model without the need to…
Multi-VFL: A Vertical Federated Learning System for Multiple Data and Label Owners
Vaikkunth Mugunthan, Pawan Goyal, Lalana Kagal
Vertical Federated Learning (VFL) refers to the collaborative training of a model on a dataset where the features of the dataset are split among multiple data owners, while label i…
Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets
Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal +1
Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive tr…
Prior-Independent Auctions for the Demand Side of Federated Learning
Andreas Haupt, Vaikkunth Mugunthan
Federated learning (FL) is a paradigm that allows distributed clients to learn a shared machine learning model without sharing their sensitive training data. While largely decentra…
DPD-InfoGAN: Differentially Private Distributed InfoGAN
Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal +1
Generative Adversarial Networks (GANs) are deep learning architectures capable of generating synthetic datasets. Despite producing high-quality synthetic images, the default GAN ha…
BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learning
Vaikkunth Mugunthan, Ravi Rahman, Lalana Kagal
Federated learning enables the development of a machine learning model among collaborating agents without requiring them to share their underlying data. However, malicious agents w…
PrivacyFL: A simulator for privacy-preserving and secure federated learning
Vaikkunth Mugunthan, Anton Peraire-Bueno, Lalana Kagal
Federated learning is a technique that enables distributed clients to collaboratively learn a shared machine learning model while keeping their training data localized. This reduce…