# Props for Machine-Learning Security

arXiv: https://arxiv.org/abs/2410.20522 · HTML: https://mlsanity.com/paper/2410.20522/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 27 Oct 2024.

## Builds on (most cited first, 14 of 14)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Will we run out of data? Limits of LLM scaling based on human-generated data](https://mlsanity.com/paper/2211.04325/) (2022)
- [Machine Learning Models that Remember Too Much](https://mlsanity.com/paper/1709.07886/) (2017)
- [Spectre Attacks: Exploiting Speculative Execution](https://mlsanity.com/paper/1801.01203/) (2018)
- [Consent in Crisis: The Rapid Decline of the AI Data Commons](https://mlsanity.com/paper/2407.14933/) (2024)
- [SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Execution](https://mlsanity.com/paper/1802.09085/) (2018)
- [DECO: Liberating Web Data Using Decentralized Oracles for TLS](https://mlsanity.com/paper/1909.00938/) (2019)
- [Intel TDX Demystified: A Top-Down Approach](https://mlsanity.com/paper/2303.15540/) (2023)

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

- [Crypto x AI, AI x Crypto: A Survey](https://mlsanity.com/paper/2606.13892/) (2026)

## Abstract (arXiv)

We propose protected pipelines or props for short, a new approach for authenticated, privacy-preserving access to deep-web data for machine learning (ML). By permitting secure use of vast sources of deep-web data, props address the systemic bottleneck of limited high-quality training data in ML development. Props also enable privacy-preserving and trustworthy forms of inference, allowing for safe use of sensitive data in ML applications. Props are practically realizable today by leveraging privacy-preserving oracle systems initially developed for blockchain applications.