# A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques

arXiv: https://arxiv.org/abs/2305.03803 · HTML: https://mlsanity.com/paper/2305.03803/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2023.

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

- [Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code](https://mlsanity.com/paper/2405.11466/) (2024)
- [Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications](https://mlsanity.com/paper/2310.05269/) (2023)
- [Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy](https://mlsanity.com/paper/2405.02828/) (2024)
- [Measuring Impacts of Poisoning on Model Parameters and Neuron Activations: A Case Study of Poisoning CodeBERT](https://mlsanity.com/paper/2402.12936/) (2024)
- [On Trojan Signatures in Large Language Models of Code](https://mlsanity.com/paper/2402.16896/) (2024)
- [Backdoors in Code Summarizers: How Bad Is It?](https://mlsanity.com/paper/2506.01825/) (2025)
- [TrojanedCM: A Repository of Trojaned Large Language Models of Code](https://mlsanity.com/paper/2311.14850/) (2023)

## Abstract (arXiv)

In this work, we study literature in Explainable AI and Safe AI to understand poisoning of neural models of code. In order to do so, we first establish a novel taxonomy for Trojan AI for code, and present a new aspect-based classification of triggers in neural models of code. Next, we highlight recent works that help us deepen our conception of how these models understand software code. Then we pick some of the recent, state-of-art poisoning strategies that can be used to manipulate such models. The insights we draw can potentially help to foster future research in the area of Trojan AI for code.