English
Related papers

Related papers: Improved Bounds for Private and Robust Alignment

200 papers

Historically, machine learning methods have not been designed with security in mind. In turn, this has given rise to adversarial examples, carefully perturbed input samples aimed to mislead detection at test time, which have been applied to…

Machine Learning · Computer Science 2022-01-11 Jamie Hayes

In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms…

Machine Learning · Statistics 2025-04-23 Soham Bonnerjee , Zhen Wei , Yeon , Anna Asch , Sagnik Nandy , Promit Ghosal

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we…

Machine Learning · Computer Science 2024-05-06 Fan Wu , Huseyin A. Inan , Arturs Backurs , Varun Chandrasekaran , Janardhan Kulkarni , Robert Sim

This paper studies privacy in the context of complex decision support queries composed of multiple conditions on different aggregate statistics combined using disjunction and conjunction operators. Utility requirements for such queries…

Databases · Computer Science 2024-06-25 Nada Lahjouji , Sameera Ghayyur , Xi He , Sharad Mehrotra

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Cryptography and Security · Computer Science 2025-08-28 Zhan Shi , Yefeng Yuan , Yuhong Liu , Liang Cheng , Yi Fang

We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private estimators with optimal…

Data Structures and Algorithms · Computer Science 2024-06-18 Samuel B. Hopkins , Gautam Kamath , Mahbod Majid , Shyam Narayanan

We study the problem of differentially private optimization with linear constraints when the right-hand-side of the constraints depends on private data. This type of problem appears in many applications, especially resource allocation.…

Machine Learning · Computer Science 2020-11-05 Andrés Muñoz Medina , Umar Syed , Sergei Vassilvitskii , Ellen Vitercik

Privacy-preserving data analysis is a rising challenge in contemporary statistics, as the privacy guarantees of statistical methods are often achieved at the expense of accuracy. In this paper, we investigate the tradeoff between…

Machine Learning · Statistics 2020-11-11 T. Tony Cai , Yichen Wang , Linjun Zhang

The widespread adoption of machine learning necessitates robust privacy protection alongside algorithmic resilience. While Local Differential Privacy (LDP) provides foundational guarantees, sophisticated adversaries with prior knowledge…

Machine Learning · Computer Science 2025-07-31 Xiaojin Zhang , Wei Chen

While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly private data.…

Machine Learning · Computer Science 2024-11-18 Vincent Hanke , Tom Blanchard , Franziska Boenisch , Iyiola Emmanuel Olatunji , Michael Backes , Adam Dziedzic

Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistical efficiency have not been formally established. This paper characterizes the conditions…

Machine Learning · Computer Science 2026-05-12 Enoch Hyunwook Kang

We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal $\tilde{O}(\sqrt{T})$ regret bounds. In the full-information setting, our results demonstrate…

Machine Learning · Computer Science 2017-06-15 Naman Agarwal , Karan Singh

We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy…

Machine Learning · Computer Science 2023-06-06 Xiaojin Zhang , Wenjie Li , Kai Chen , Shutao Xia , Qiang Yang

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm,…

Machine Learning · Computer Science 2018-03-28 Thodoris Lykouris , Vahab Mirrokni , Renato Paes Leme

In linear bandits, how can a learner effectively learn when facing corrupted rewards? While significant work has explored this question, a holistic understanding across different adversarial models and corruption measures is lacking, as is…

Machine Learning · Computer Science 2024-10-21 Haolin Liu , Artin Tajdini , Andrew Wagenmaker , Chen-Yu Wei

We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant…

Machine Learning · Statistics 2022-12-02 Kristian Georgiev , Samuel B. Hopkins

In statistical learning and analysis from shared data, which is increasingly widely adopted in platforms such as federated learning and meta-learning, there are two major concerns: privacy and robustness. Each participating individual…

Machine Learning · Computer Science 2021-11-25 Xiyang Liu , Weihao Kong , Sham Kakade , Sewoong Oh

This paper considers two fundamental sequential decision-making problems: the problem of prediction with expert advice and the multi-armed bandit problem. We focus on stochastic regimes in which an adversary may corrupt losses, and we…

Machine Learning · Statistics 2021-09-24 Shinji Ito

This paper addresses online learning with ``corrupted'' feedback. Our learner is provided with potentially corrupted gradients $\tilde g_t$ instead of the ``true'' gradients $g_t$. We make no assumptions about how the corruptions arise:…

Machine Learning · Computer Science 2025-06-17 Jiujia Zhang , Ashok Cutkosky

The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…

Cryptography and Security · Computer Science 2024-12-10 Guoshenghui Zhao , Eric Song