23 citations · 62 across the 50 of their papers we have counts for
58 papers
CALLIOPE: Private Insights into AI Use, Without Embeddings
Edith Cohen, Vadym Doroshenko, Badih Ghazi +11
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g., LLM conversations), while supporting differential privacy…
Differential Privacy Meets Fixed Parameter Tractability: Algorithms and Lower Bounds
Pritish Kamath, Ravi Kumar, Pasin Manurangsi
We study combinatorial optimization problems under the constraint of -differential privacy (-DP). Given the strong lower bounds for explicitly outputting solutions, we work w…
Overcoming the Randomness-Utility Trade-off in Answering Differentially Private Linear Queries
Surendra Ghentiyala, Pritish Kamath, Ravi Kumar +1
We study the question of answering linear queries with differential privacy using few (expected) random bits. We provide a randomness-efficient analog of the -norm m…
Online Differentially Private Consistent Clustering
Edith Cohen, Vadym Doroshenko, Badih Ghazi +7
We study differentially private (DP) -means and -median clustering in the online streaming setting. In this model, points arrive sequentially, and at each time step, we need…
Fixed-Parameter Tractability of Private Synthetic Data Generation
Badih Ghazi, Cristóbal Guzmán, Pritish Kamath +3
We study the problem of generating synthetic data under differential privacy. We establish fixed-parameter tractability (FPT) for this problem where the parameter is the treewidth…
When Majority Fails: Tight Bounds for Correlation Distillation Conjectures
Pritish Kamath, Ravi Kumar, Pasin Manurangsi
We study two conjectures posed in the analysis of Boolean functions , in both of which, the Majority function plays a central role: the "Majority is…
Denoising the US Census: Succinct Block Hierarchical Regression
Badih Ghazi, Pritish Kamath, Ravi Kumar +2
The US Census Bureau Disclosure Avoidance System (DAS) balances confidentiality and utility requirements for the decennial US Census (Abowd et al., 2022). The DAS was used in the 2…
Computational Hardness of Private Coreset
Badih Ghazi, Cristóbal Guzmán, Pritish Kamath +3
We study the problem of differentially private (DP) computation of coreset for the -means objective. For a given input set of points, a coreset is another set of points such tha…
VaultGemma: A Differentially Private Gemma Model
Amer Sinha, Thomas Mesnard, Ryan McKenna +18
We introduce VaultGemma 1B, a 1 billion parameter model within the Gemma family, fully trained with differential privacy. Pretrained on the identical data mixture used for the Gemm…
Private Hyperparameter Tuning with Ex-Post Guarantee
Badih Ghazi, Pritish Kamath, Alexander Knop +3
The conventional approach in differential privacy (DP) literature formulates the privacy-utility trade-off with a "privacy-first" perspective: for a predetermined level of privacy,…
Urania: Differentially Private Insights into AI Use
Daogao Liu, Edith Cohen, Badih Ghazi +8
We introduce , a novel framework for generating insights about LLM chatbot interactions with rigorous differential privacy (DP) guarantees. The framework employs a private…
Empirical Privacy Variance
Yuzheng Hu, Fan Wu, Ruicheng Xian +5
We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrat…
PREM: Privately Answering Statistical Queries with Relative Error
Badih Ghazi, Cristóbal Guzmán, Pritish Kamath +4
We introduce (Private Relative Error Multiplicative weight update), a new framework for generating synthetic data that achieves a relative error guarantee for stati…
Scaling Embedding Layers in Language Models
Da Yu, Edith Cohen, Badih Ghazi +5
We propose (calable, ontextualized, ffloaded, -gram mbedding), a new method for extending input embedding layers to enhance language model performance. To av…
On the Differential Privacy and Interactivity of Privacy Sandbox Reports
Badih Ghazi, Charlie Harrison, Arpana Hosabettu +8
The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving advertising functionalities as part of the effort around limiting third-party cookies. In p…
Balls-and-Bins Sampling for DP-SGD
Lynn Chua, Badih Ghazi, Charlie Harrison +6
We introduce the Balls-and-Bins sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-…
How Unique is Whose Web Browser? The role of demographics in browser fingerprinting among US users
Alex Berke, Enrico Bacis, Badih Ghazi +5
Browser fingerprinting can be used to identify and track users across the Web, even without cookies, by collecting attributes from users' devices to create unique "fingerprints". T…
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
Lynn Chua, Badih Ghazi, Pritish Kamath +4
We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Batch Linear Queries (ABLQ) mechanism with shuffled batch sampling, demonstrating substantial gaps…
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
Yangsibo Huang, Daogao Liu, Lynn Chua +7
Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expos…
On Convex Optimization with Semi-Sensitive Features
Badih Ghazi, Pritish Kamath, Ravi Kumar +3
We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive. This generalizes the…
Learning Neural Networks with Sparse Activations
Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath +1
A core component present in many successful neural network architectures, is an MLP block of two fully connected layers with a non-linear activation in between. An intriguing pheno…
On Computing Pairwise Statistics with Local Differential Privacy
Badih Ghazi, Pritish Kamath, Ravi Kumar +2
We study the problem of computing pairwise statistics, i.e., ones of the form , where denotes the input to the th user, with…
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
Lynn Chua, Badih Ghazi, Yangsibo Huang +6
Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, i.e…
Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
Lynn Chua, Badih Ghazi, Yangsibo Huang +6
Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive dat…