14 citations · 49 across the 26 of their papers we have counts for
28 papers
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Sarim Hashmi, Mukul Ranjan, Kshitij Mishra +3
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The…
Modulated learning for private and distributed regression with just a single sample per client device
Praneeth Vepakomma, Amirhossein Reisizadeh, Samuel Horváth +1
This work focuses on the question of learning from a large number of devices with each device holding only a single sample of data. Several real-world applications exist to this on…
Combinatorial Privacy: Private Multi-Party Bitstream Grand Sum by Hiding in Birkhoff Polytopes
Praneeth Vepakomma
We introduce PolyVeil, a protocol for private Boolean summation across clients that encodes private bits as permutation matrices in the Birkhoff polytope. A two-layer architect…
Learning in the Null Space: Small Singular Values for Continual Learning
Cuong Anh Pham, Praneeth Vepakomma, Samuel Horváth
Alleviating catastrophic forgetting while enabling further learning is a primary challenge in continual learning (CL). Orthogonal-based training methods have gained attention for t…
Offline and Online KL-Regularized RLHF under Differential Privacy
Yulian Wu, Rushil Thareja, Praneeth Vepakomma +1
In this paper, we study the offline and online settings of reinforcement learning from human feedback (RLHF) with KL-regularization -- a widely used objective function in large lan…
Power Mechanism: Private Tabular Representation Release for Model Agnostic Consumption
Praneeth Vepakomma, Kaustubh Ponkshe
Traditional collaborative learning approaches are based on sharing of model weights between clients and a server. However, there are advantages to resource efficiency through schem…
DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
Rushil Thareja, Preslav Nakov, Praneeth Vepakomma +1
Large language models (LLMs) do not preserve privacy at inference-time. The LLM's outputs can inadvertently reveal information about the model's context, which presents a privacy c…
HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models
Zheng Lin, Yuxin Zhang, Zhe Chen +6
Recently, large language models (LLMs) have achieved remarkable breakthroughs, revolutionizing the natural language processing domain and beyond. Due to immense parameter sizes, fi…
ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak +1
Large Language Models have demonstrated strong performance across a wide range of tasks, but adapting them efficiently to new domains remains a key challenge. Parameter-Efficient F…
Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study
Kaustubh Ponkshe, Shaan Shah, Raghav Singhal +1
Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign o…
Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning
Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak +2
Low-Rank Adaptation (LoRA) has become ubiquitous for efficiently fine-tuning foundation models. However, federated fine-tuning using LoRA is challenging due to suboptimal updates a…
Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach
Chaouki Ben Issaid, Praneeth Vepakomma, Mehdi Bennis
Federated multi-task learning (FMTL) aims to simultaneously learn multiple related tasks across clients without sharing sensitive raw data. However, in the decentralized setting, e…
Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning
Kaustubh Ponkshe, Raghav Singhal, Eduard Gorbunov +3
Low-rank adapters have become standard for efficiently fine-tuning large language models, but they often fall short of achieving the performance of full fine-tuning. We propose a m…
FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models
Raghav Singhal, Kaustubh Ponkshe, Praneeth Vepakomma
Low-Rank Adaptation (LoRA) is a popular technique for efficient fine-tuning of foundation models. However, applying LoRA in federated learning environments, where data is distribut…
Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix
Seungeun Oh, Sihun Baek, Jihong Park +5
In computer vision, the vision transformer (ViT) has increasingly superseded the convolutional neural network (CNN) for improved accuracy and robustness. However, ViT's large model…
SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models
Zheng Lin, Xuanjie Hu, Yuxin Zhang +6
The scalability of large language models (LLMs) in handling high-complexity models and large-scale datasets has led to tremendous successes in pivotal domains. While there is an ur…
DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images
Zaid Tasneem, Akshat Dave, Abhishek Singh +4
Neural radiance fields (NeRFs) show potential for transforming images captured worldwide into immersive 3D visual experiences. However, most of this captured visual data remains si…
DAVED: Data Acquisition via Experimental Design for Data Markets
Charles Lu, Baihe Huang, Sai Praneeth Karimireddy +3
The acquisition of training data is crucial for machine learning applications. Data markets can increase the supply of data, particularly in data-scarce domains such as healthcare,…
Differentially Private CutMix for Split Learning with Vision Transformer
Seungeun Oh, Jihong Park, Sihun Baek +5
Recently, vision transformer (ViT) has started to outpace the conventional CNN in computer vision tasks. Considering privacy-preserving distributed learning with ViT, federated lea…
Differentially Private Fréchet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices with log-Euclidean Metric
Saiteja Utpala, Praneeth Vepakomma, Nina Miolane
Differential privacy has become crucial in the real-world deployment of statistical and machine learning algorithms with rigorous privacy guarantees. The earliest statistical queri…
Private independence testing across two parties
Praneeth Vepakomma, Mohammad Mohammadi Amiri, Clément L. Canonne +2
We introduce -test, a privacy-preserving algorithm for testing statistical independence between data distributed across multiple parties. Our algorithm relies on privately estim…
Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning
Sihun Baek, Jihong Park, Praneeth Vepakomma +3
This article seeks for a distributed learning solution for the visual transformer (ViT) architectures. Compared to convolutional neural network (CNN) architectures, ViTs often have…
Decouple-and-Sample: Protecting sensitive information in task agnostic data release
Abhishek Singh, Ethan Garza, Ayush Chopra +3
We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in various applications of computer vision, its…
Effects of Privacy-Inducing Noise on Welfare and Influence of Referendum Systems
Suat Evren, Praneeth Vepakomma
Social choice functions help aggregate individual preferences while differentially private mechanisms provide formal privacy guarantees to release answers of queries operating on s…