paper-with-me

홈 › Papers

Rainbow Differential Privacy

2022-02-08 · Ziqi Zhou, Onur Günlü, Rafael G. L. D'Oliveira, Muriel Médard, Parastoo Sadeghi, Rafael F. Schaefer

We extend a previous framework for designing differentially private (DP) mechanisms via randomized graph colorings that was restricted to binary functions, corresponding to colorings in a graph, to multi-valued functions. As before, datasets are nodes in the graph and any two neighboring datasets are connected by an edge. In our setting, we assume that each dataset has a preferential ordering for the possible outputs of the mechanism, each of which we refer to as a rainbow. Different rainbows partition the graph of datasets into different regions. We show that if the DP mechanism is pre-specified at the boundary of such regions and behaves identically for all same-rainbow boundary datasets, at most one optimal such mechanism can exist and the problem can be solved by means of a morphism to a line graph. We then show closed form expressions for the line graph in the case of ternary functions. Treatment of ternary queries in this paper displays enough richness to be extended to higher-dimensional query spaces with preferential query ordering, but the optimality proof does not seem to follow directly from the ternary proof.

📄 PDF Abstract BibTeX arXiv:2202.03974

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generalized Rainbow Differential Privacy

2023-09-11 · Yuzhou Gu, Ziqi Zhou, Onur Günlü, Rafael G. L. D'Oliveira 외

We study a new framework for designing differentially private (DP) mechanisms via randomized graph colorings, called rainbow differential privacy. In this framework, datasets are nodes in a graph, and two neighboring dat…

valid

Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari

2021-11-19 · Dominik Schmidt, Thomas Schmied

Across the Arcade Learning Environment, Rainbow achieves a level of performance competitive with humans and modern RL algorithms. However, attaining this level of performance requires large amounts of data and hardware r…

Atari GamesGPU

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

2024-02-26 · Mikayel Samvelyan, Sharath Chandra Raparthy, Andrei Lupu, Eric Hambro 외

As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to adversarial attacks is of paramount importance. Existing methods for iden…

DiversityQuestion Answering

RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search

2025-04-21 · Quy-Anh Dang, Chris Ngo, Truong-Son Hy

Large Language Models (LLMs) exhibit remarkable capabilities but are susceptible to adversarial prompts that exploit vulnerabilities to produce unsafe or biased outputs. Existing red-teaming methods often face scalabilit…

DiversityEvolutionary AlgorithmsRed Teaming

Variational Quantum Rainbow Deep Q-Network for Optimizing Resource Allocation Problem

2025-12-05 · Truong Thanh Hung Nguyen, Truong Thinh Nguyen, Hung Cao arxiv

Resource allocation remains NP-hard due to combinatorial complexity. While deep reinforcement learning (DRL) methods, such as the Rainbow Deep Q-Network (DQN), improve scalability through prioritized replay and distribut…

Reinforcement Learning