paper-with-me

Papers

Defending against Reconstruction Attacks with Rényi Differential Privacy

2022-02-15 · Pierre Stock, Igor Shilov, Ilya Mironov, Alexandre Sablayrolles

Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can reconstruct data samples from language models, making this threat scenario an important aspect of model release. Differential privacy is a known solution to such attacks, but is often used with a relatively large privacy budget (epsilon > 8) which does not translate to meaningful guarantees. In this paper we show that, for a same mechanism, we can derive privacy guarantees for reconstruction attacks that are better than the traditional ones from the literature. In particular, we show that larger privacy budgets do not protect against membership inference, but can still protect extraction of rare secrets. We show experimentally that our guarantees hold against various language models, including GPT-2 finetuned on Wikitext-103.

📄 PDF Abstract BibTeX arXiv:2202.07623

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Similar Papers 제목 키워드 기반

Does Differential Privacy Prevent Backdoor Attacks in Practice?

2023-11-10 · Fereshteh Razmi, Jian Lou, Li Xiong

Differential Privacy (DP) was originally developed to protect privacy. However, it has recently been utilized to secure machine learning (ML) models from poisoning attacks, with DP-SGD receiving substantial attention. Ne…

Visual Privacy Auditing with Diffusion Models

2024-03-12 · Kristian Schwethelm, Johannes Kaiser, Moritz Knolle, Sarah Lockfisch 외

Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) provides the…

Image ReconstructionReconstruction Attack

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-Ray Data

2022-05-06 · Joceline Ziegler, Bjarne Pfitzner, Heinrich Schulz, Axel Saalbach 외

Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially …

Binary ClassificationFederated LearningImage ReconstructionX-ray Classification

One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy

2022-03-13 · Dayong Ye, Sheng Shen, Tianqing Zhu, Bo Liu 외

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a datas…

The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization

2025-08-26 · Stephen Meisenbacher, Alexandra Klymenko, Andreea-Elena Bodea, Florian Matthes arxiv

Differentially private text sanitization refers to the process of privatizing texts under the framework of Differential Privacy (DP), providing provable privacy guarantees while also empirically defending against adversa…