English
Related papers

Related papers: Improved Bounds for Private and Robust Alignment

200 papers

In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets. Traditional robust methods can handle the noise but suffer…

Data Structures and Algorithms · Computer Science 2017-10-04 Xuchao Zhang , Liang Zhao , Arnold P. Boedihardjo , Chang-Tien Lu

We consider offline Imitation Learning from corrupted demonstrations where a constant fraction of data can be noise or even arbitrary outliers. Classical approaches such as Behavior Cloning assumes that demonstrations are collected by an…

Machine Learning · Computer Science 2022-02-01 Liu Liu , Ziyang Tang , Lanqing Li , Dijun Luo

We study the problem of improving the performance of online algorithms by incorporating machine-learned predictions. The goal is to design algorithms that are both consistent and robust, meaning that the algorithm performs well when…

Machine Learning · Computer Science 2020-10-23 Alexander Wei , Fred Zhang

Contextual bandit with linear reward functions is among one of the most extensively studied models in bandit and online learning research. Recently, there has been increasing interest in designing \emph{locally private} linear contextual…

Machine Learning · Statistics 2024-04-16 Jiachun Li , David Simchi-Levi , Yining Wang

Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients'…

Machine Learning · Computer Science 2025-01-22 Haonan Shi , Tu Ouyang , An Wang

Communicating anonymously comes at a cost - and large communities have been in a constant tug-of-war between the development of faster protocols, and the improvement of security analyses. Thereby more intricate privacy goals emerged and…

Cryptography and Security · Computer Science 2020-11-18 Christiane Kuhn , Friederike Kitzing , Thorsten Strufe

With changes in privacy laws, there is often a hard requirement for client data to remain on the device rather than being sent to the server. Therefore, most processing happens on the device, and only an altered element is sent to the…

Cryptography and Security · Computer Science 2022-12-27 Ajinkya K Mulay

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While…

Computation and Language · Computer Science 2023-07-13 Yahan Yang , Soham Dan , Dan Roth , Insup Lee

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

The performance of machine learning algorithms can be considerably improved when trained over larger datasets. In many domains, such as medicine and finance, larger datasets can be obtained if several parties, each having access to limited…

Machine Learning · Computer Science 2021-09-30 Dana Pessach , Tamir Tassa , Erez Shmueli

In supervised learning one wishes to identify a pattern present in a joint distribution $P$, of instances, label pairs, by providing a function $f$ from instances to labels that has low risk $\mathbb{E}_{P}\ell(y,f(x))$. To do so, the…

Machine Learning · Statistics 2015-07-07 Brendan van Rooyen , Robert C. Williamson

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly)…

Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…

Cryptography and Security · Computer Science 2026-04-28 Zihan Liu , Yizhen Wang , Rui Wang , Xiu Tang , Sai Wu

As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias as the appropriateness value of information flows in responses from LLMs. A…

Machine Learning · Computer Science 2025-12-22 Yan Shvartzshnaider , Vasisht Duddu

Organizations are collecting vast amounts of data, but they often lack the capabilities needed to fully extract insights. As a result, they increasingly share data with external experts, such as analysts or researchers, to gain value from…

Machine Learning · Computer Science 2025-05-16 Yusi Wei , Hande Y. Benson , Joseph K. Agor , Muge Capan

Practical and pervasive needs for robustness and privacy in algorithms have inspired the design of online adversarial and differentially private learning algorithms. The primary quantity that characterizes learnability in these settings is…

Machine Learning · Computer Science 2020-06-19 Nika Haghtalab , Tim Roughgarden , Abhishek Shetty

We study binary classification in the setting where the learner is presented with multiple corrupted training samples, with possibly different sample sizes and degrees of corruption, and introduce an approach based on minimizing a weighted…

Machine Learning · Statistics 2019-10-11 Clayton Scott , Jianxin Zhang

Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…

Machine Learning · Computer Science 2025-10-27 Jerry Huang , Peng Lu , Qiuhao Zeng

We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions. In this setting, every time before the learner observes a sample, the adversary decides whether to…

Machine Learning · Computer Science 2021-06-22 Yifang Chen , Simon S. Du , Kevin Jamieson

Differential privacy (DP) provides rigorous privacy guarantees on individual's data while also allowing for accurate statistics to be conducted on the overall, sensitive dataset. To design a private system, first private algorithms must be…

Cryptography and Security · Computer Science 2020-11-19 Mark Cesar , Ryan Rogers