Exploiting ML models with pickle file attacks: Part 1

Published

2024-06-11 13:00

Collected

2026-07-03 03:46

---
id: 1495
title: "Exploiting ML models with pickle file attacks: Part 1"
source_domain: blog.trailofbits.com
source_url: "https://blog.trailofbits.com/2024/06/11/exploiting-ml-models-with-pickle-file-attacks-part-1/"
published_at: "2024-06-11 13:00"
tags: ["deserialization", "python", "machine-learning", "attack-techniques", "supply-chain-security", "pickle"]
phying_url: "https://phying.com/item/1495"
lang: en
---

# Exploiting ML models with pickle file attacks: Part 1

## Summary

Trail of Bits' Sleepy Pickle technique embeds malicious payloads in ML model pickle files, compromising the model itself to steal data, spread disinformation, or phish end users.

## Intelligence Metadata

- **Sources:** blog.trailofbits.com
- **Published:** 2024-06-11 13:00
- **Original:** https://blog.trailofbits.com/2024/06/11/exploiting-ml-models-with-pickle-file-attacks-part-1/
- **Phying News:** https://phying.com/item/1495