# Backdoor Attacks to Pre-trained Unified Foundation Models

arXiv: https://arxiv.org/abs/2302.09360 · HTML: https://mlsanity.com/paper/2302.09360/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 7 of its 8 references that are in the map.
- First posted on arXiv 18 Feb 2023.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 7 of 7)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning](https://mlsanity.com/paper/2108.00352/) (2021)
- [BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models](https://mlsanity.com/paper/2110.02467/) (2021)

## Built on by (most cited first, 7 of 7)

- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review](https://mlsanity.com/paper/2309.06055/) (2023)
- [Artificial General Intelligence for Medical Imaging Analysis](https://mlsanity.com/paper/2306.05480/) (2023)
- [BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models](https://mlsanity.com/paper/2503.16023/) (2025)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks](https://mlsanity.com/paper/2305.03289/) (2023)
- [Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models](https://mlsanity.com/paper/2505.23561/) (2025)

## Abstract (arXiv)

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses a serious threat to their security. Previous research on backdoor attacks has been limited to uni-modal tasks or single tasks across modalities, making it inapplicable to unified foundation models. In this paper, we make proof-of-concept level research on the backdoor attack for pre-trained unified foundation models. Through preliminary experiments on NLP and CV classification tasks, we reveal the vulnerability of these models and suggest future research directions for enhancing the attack approach.