Search Results for author: Victor Rühle

Found 7 papers, 2 papers with code

Analyzing Information Leakage of Updates to Natural Language Models

no code implementations17 Dec 2019 Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Victor Rühle, Andrew Paverd, Olga Ohrimenko, Boris Köpf, Marc Brockschmidt

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models.

Language Modelling

Training Data Leakage Analysis in Language Models

no code implementations14 Jan 2021 Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, Robert Sim

It has been demonstrated that strong performance of language models comes along with the ability to memorize rare training samples, which poses serious privacy threats in case the model is trained on confidential user content.

Sentence

Privacy Regularization: Joint Privacy-Utility Optimization in Language Models

no code implementations12 Mar 2021 FatemehSadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim

In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a triplet-loss term.

Memorization Privacy Preserving

Bayesian Estimation of Differential Privacy

1 code implementation10 Jun 2022 Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Rühle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones

Our Bayesian method exploits the hypothesis testing interpretation of differential privacy to obtain a posterior for $\varepsilon$ (not just a confidence interval) from the joint posterior of the false positive and false negative rates of membership inference attacks.

Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective

no code implementations27 Nov 2023 Lukas Wutschitz, Boris Köpf, Andrew Paverd, Saravan Rajmohan, Ahmed Salem, Shruti Tople, Santiago Zanella-Béguelin, Menglin Xia, Victor Rühle

In this paper, we take an information flow control perspective to describe machine learning systems, which allows us to leverage metadata such as access control policies and define clear-cut privacy and confidentiality guarantees with interpretable information flows.

Retrieval

Unlocking Spatial Comprehension in Text-to-Image Diffusion Models

no code implementations28 Nov 2023 Mohammad Mahdi Derakhshani, Menglin Xia, Harkirat Behl, Cees G. M. Snoek, Victor Rühle

We propose CompFuser, an image generation pipeline that enhances spatial comprehension and attribute assignment in text-to-image generative models.

Attribute Image Generation +3

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

1 code implementation19 Mar 2024 Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, QIngwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Dongmei Zhang

The challenge is that information entropy may be a suboptimal compression metric: (i) it only leverages unidirectional context and may fail to capture all essential information needed for prompt compression; (ii) it is not aligned with the prompt compression objective.

GSM8K Language Modelling +3

Cannot find the paper you are looking for? You can Submit a new open access paper.