# Learning to Generate Cross-Task Unexploitable Examples

arXiv: https://arxiv.org/abs/2512.13416 · HTML: https://mlsanity.com/paper/2512.13416/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 61 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Builds on (most cited first, 30 of 44)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives](https://mlsanity.com/paper/1407.0202/) (2014)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout](https://mlsanity.com/paper/2010.06808/) (2020)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Minimizing Finite Sums with the Stochastic Average Gradient](https://mlsanity.com/paper/1309.2388/) (2013)
- [Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning](https://mlsanity.com/paper/2202.03599/) (2022)
- [Adversarial Examples Make Strong Poisons](https://mlsanity.com/paper/2106.10807/) (2021)
- [Availability Attacks Create Shortcuts](https://mlsanity.com/paper/2111.00898/) (2021)
- [Learning Meta Face Recognition in Unseen Domains](https://mlsanity.com/paper/2003.07733/) (2020)
- [Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning](https://mlsanity.com/paper/2206.03996/) (2022)
- [On the Maximum Hessian Eigenvalue and Generalization](https://mlsanity.com/paper/2206.10654/) (2022)
- [Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization](https://mlsanity.com/paper/2303.03108/) (2023)
- [Autoregressive Perturbations for Data Poisoning](https://mlsanity.com/paper/2206.03693/) (2022)
- [A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization](https://mlsanity.com/paper/2012.03801/) (2020)
- [Transferable Unlearnable Examples](https://mlsanity.com/paper/2210.10114/) (2022)
- [Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation](https://mlsanity.com/paper/2306.01902/) (2023)

## Abstract (arXiv)

Unexploitable example generation aims to transform personal images into their unexploitable (unlearnable) versions before they are uploaded online, thereby preventing unauthorized exploitation of online personal images. Recently, this task has garnered significant research attention due to its critical relevance to personal data privacy. Yet, despite recent progress, existing methods for this task can still suffer from limited practical applicability, as they can fail to generate examples that are broadly unexploitable across different real-world computer vision tasks. To deal with this problem, in this work, we propose a novel Meta Cross-Task Unexploitable Example Generation (MCT-UEG) framework. At the core of our framework, to optimize the unexploitable example generator for effectively producing broadly unexploitable examples, we design a flat-minima-oriented meta training and testing scheme. Extensive experiments show the efficacy of our framework.