Privacy-Aware In-Context Learning for Large Language Models
Bishnu Bhusal, Manoj Acharya, Ramneet Kaur, Colin Samplawski, Anirban Roy, Adam D. Cobb, Rohit Chadha, Susmit Jha
http://arxiv.org/abs/2509.13625
Large language models (LLMs) have significantly transformed natural language
understanding and generation, but they raise privacy concerns due to potential
exposure of sensitive information. Studies have highlighted the risk of
information leakage, where adversaries can extract sensitive information
embedded in the prompts. In this work, we introduce a novel private prediction
framework for generating high-quality synthetic text with strong privacy
guarantees. Our approach leverages the Differential Privacy (DP) framework to
ensure worst-case theoretical bounds on information leakage without requiring
any fine-tuning of the underlying models.The proposed method performs inference
on private records and aggregates the resulting per-token output distributions.
This enables the generation of longer and coherent synthetic text while
maintaining privacy guarantees. Additionally, we propose a simple blending
operation that combines private and public inference to further enhance
utility. Empirical evaluations demonstrate that our approach outperforms
previous state-of-the-art methods on in-context-learning (ICL) tasks, making it
a promising direction for privacy-preserving text generation while maintaining
high utility.
Privacy-Aware In-Context Learning for Large Language Models
Bishnu Bhusal, Manoj Acharya, Ramneet Kaur, Colin Samplawski, Anirban Roy, Adam D. Cobb, Rohit Chadha, Susmit Jha
http://arxiv.org/abs/2509.13625
18.09.2025 03:49 — 👍 0 🔁 1 💬 0 📌 0
Approximate Algorithms for Verifying Differential Privacy with Gaussian Distributions
Bishnu Bhusal, Rohit Chadha, A. Prasad Sistla, Mahesh Viswanathan
http://arxiv.org/abs/2509.08804
The verification of differential privacy algorithms that employ Gaussian
distributions is little understood. This paper tackles the challenge of
verifying such programs by introducing a novel approach to approximating
probability distributions of loop-free programs that sample from both discrete
and continuous distributions with computable probability density functions,
including Gaussian and Laplace. We establish that verifying
$(\epsilon,\delta)$-differential privacy for these programs is \emph{almost
decidable}, meaning the problem is decidable for all values of $\delta$ except
those in a finite set. Our verification algorithm is based on computing
probabilities to any desired precision by combining integral approximations,
and tail probability bounds. The proposed methods are implemented in the tool,
DipApprox, using the FLINT library for high-precision integral computations,
and incorporate optimizations to enhance scalability. We validate {\ourtool} on
fundamental privacy-preserving algorithms, such as Gaussian variants of the
Sparse Vector Technique and Noisy Max, demonstrating its effectiveness in both
confirming privacy guarantees and detecting violations.
Approximate Algorithms for Verifying Differential Privacy with Gaussian Distributions
Bishnu Bhusal, Rohit Chadha, A. Prasad Sistla, Mahesh Viswanathan
http://arxiv.org/abs/2509.08804
11.09.2025 03:48 — 👍 0 🔁 1 💬 0 📌 0
LinkedIn
This link will take you to a page that’s not on LinkedIn
Excited to share that our paper “Checking δ-Satisfiability of Reals with Integrals” is now published in the Proceedings of the ACM on Programming Languages!
We extend δ-decision procedures to handle constraints involving integrals of real functions.
Paper: dl.acm.org/doi/10.1145/...
10.04.2025 00:34 — 👍 0 🔁 0 💬 0 📌 0
