# Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure

arXiv: https://arxiv.org/abs/2512.16126 · HTML: https://mlsanity.com/paper/2512.16126/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 34 of its 58 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Membership Leakage in Label-Only Exposures](https://mlsanity.com/paper/2007.15528/) (2020)
- [AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning](https://mlsanity.com/paper/2308.07026/) (2023)
- [Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy](https://mlsanity.com/paper/2403.01218/) (2024)
- [Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning](https://mlsanity.com/paper/2404.03233/) (2024)
- [Amplifying Membership Exposure via Data Poisoning](https://mlsanity.com/paper/2211.00463/) (2022)
- [DarkSAM: Fooling Segment Anything Model to Segment Nothing](https://mlsanity.com/paper/2409.17874/) (2024)
- [BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label](https://mlsanity.com/paper/2207.00278/) (2022)
- [Transferable Adversarial Facial Images for Privacy Protection](https://mlsanity.com/paper/2408.01428/) (2024)
- [Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable](https://mlsanity.com/paper/2405.20272/) (2024)
- [ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents](https://mlsanity.com/paper/2509.16645/) (2025)
- [Exact and Efficient Unlearning for Large Language Model-based Recommendation](https://mlsanity.com/paper/2404.10327/) (2024)
- [NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors](https://mlsanity.com/paper/2412.16955/) (2024)
- [Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature](https://mlsanity.com/paper/2412.16958/) (2024)
- [Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2](https://mlsanity.com/paper/2510.24195/) (2025)
- [Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM](https://mlsanity.com/paper/2505.23828/) (2025)

## Built on by (most cited first, 1 of 1)

- [UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion](https://mlsanity.com/paper/2601.20325/) (2026)

## Abstract (arXiv)

Machine unlearning is a newly popularized technique for removing specific training data from a trained model, enabling it to comply with data deletion requests. While it protects the rights of users requesting unlearning, it also introduces new privacy risks. Prior works have primarily focused on the privacy of data that has been unlearned, while the risks to retained data remain largely unexplored. To address this gap, we focus on the privacy risks of retained data and, for the first time, reveal the vulnerabilities introduced by machine unlearning under the dual-view setting, where an adversary can query both the original and the unlearned models. From an information-theoretic perspective, we introduce the concept of {privacy knowledge gain} and demonstrate that the dual-view setting allows adversaries to obtain more information than querying either model alone, thereby amplifying privacy leakage. To effectively demonstrate this threat, we propose DVIA, a Dual-View Inference Attack, which extracts membership information on retained data using black-box queries to both models. DVIA eliminates the need to train an attack model and employs a lightweight likelihood ratio inference module for efficient inference. Experiments across different datasets and model architectures validate the effectiveness of DVIA and highlight the privacy risks inherent in the dual-view setting.