# Human intuition as a defense against attribute inference

arXiv: https://arxiv.org/abs/2304.11853 · HTML: https://mlsanity.com/paper/2304.11853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 67 references that are in the map.
- First posted on arXiv 24 Apr 2023.

## Builds on (most cited first, 13 of 13)

- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Revisiting IM2GPS in the Deep Learning Era](https://mlsanity.com/paper/1705.04838/) (2017)
- [Hiding Individuals and Communities in a Social Network](https://mlsanity.com/paper/1608.00375/) (2016)
- [Automated Poisoning Attacks and Defenses in Malware Detection Systems: An Adversarial Machine Learning Approach](https://mlsanity.com/paper/1706.04146/) (2017)
- [Man vs the machine: The Struggle for Effective Text Anonymisation in the Age of Large Language Models](https://mlsanity.com/paper/2303.12429/) (2023)
- [Protecting Geolocation Privacy of Photo Collections](https://mlsanity.com/paper/1912.02085/) (2019)
- [Covert Networks: How Hard is It to Hide?](https://mlsanity.com/paper/1903.05832/) (2019)
- [Hiding in Multilayer Networks](https://mlsanity.com/paper/1911.05947/) (2019)
- [Strategic Evasion of Centrality Measures](https://mlsanity.com/paper/2101.10648/) (2021)
- [Social Diffusion Sources Can Escape Detection](https://mlsanity.com/paper/2102.10539/) (2021)
- [Hiding in Temporal Networks](https://mlsanity.com/paper/2107.13174/) (2021)

## Abstract (arXiv)

Attribute inference - the process of analyzing publicly available data in order to uncover hidden information - has become a major threat to privacy, given the recent technological leap in machine learning. One way to tackle this threat is to strategically modify one's publicly available data in order to keep one's private information hidden from attribute inference. We evaluate people's ability to perform this task, and compare it against algorithms designed for this purpose. We focus on three attributes: the gender of the author of a piece of text, the country in which a set of photos was taken, and the link missing from a social network. For each of these attributes, we find that people's effectiveness is inferior to that of AI, especially when it comes to hiding the attribute in question. Moreover, when people are asked to modify the publicly available information in order to hide these attributes, they are less likely to make high-impact modifications compared to AI. This suggests that people are unable to recognize the aspects of the data that are critical to an inference algorithm. Taken together, our findings highlight the limitations of relying on human intuition to protect privacy in the age of AI, and emphasize the need for algorithmic support to protect private information from attribute inference.