# Multi-target Backdoor Attacks for Code Pre-trained Models

arXiv: https://arxiv.org/abs/2306.08350 · HTML: https://mlsanity.com/paper/2306.08350/

## Key facts

- Cited by 23 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 38 of its 55 references that are in the map.
- First posted on arXiv 14 Jun 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, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://mlsanity.com/paper/2011.10369/) (2020)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion](https://mlsanity.com/paper/2007.02220/) (2020)
- [An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation](https://mlsanity.com/paper/1812.08693/) (2018)
- [Backdoor Pre-trained Models Can Transfer to All](https://mlsanity.com/paper/2111.00197/) (2021)
- [BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models](https://mlsanity.com/paper/2110.02467/) (2021)
- [Adversarial Examples for Models of Code](https://mlsanity.com/paper/1910.07517/) (2019)
- [SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation](https://mlsanity.com/paper/2108.04556/) (2021)
- [Self-Supervised Bug Detection and Repair](https://mlsanity.com/paper/2105.12787/) (2021)
- [Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks](https://mlsanity.com/paper/2101.06969/) (2021)
- [Stealthy Backdoor Attack for Code Models](https://mlsanity.com/paper/2301.02496/) (2023)

## Built on by (most cited first, 23 of 23)

- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [BadEdit: Backdooring large language models by model editing](https://mlsanity.com/paper/2403.13355/) (2024)
- [An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection](https://mlsanity.com/paper/2406.06822/) (2024)
- [Compromising Embodied Agents with Contextual Backdoor Attacks](https://mlsanity.com/paper/2408.02882/) (2024)
- [Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks](https://mlsanity.com/paper/2405.12725/) (2024)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [SandboxEval: Towards Securing Test Environment for Untrusted Code](https://mlsanity.com/paper/2504.00018/) (2025)
- [Control Tax: The Price of Keeping AI in Check](https://mlsanity.com/paper/2506.05296/) (2025)
- [Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation](https://mlsanity.com/paper/2510.18541/) (2025)
- [Neutralizing Backdoors through Information Conflicts for Large Language Models](https://mlsanity.com/paper/2411.18280/) (2024)
- [Watermarking LLM Agent Trajectories](https://mlsanity.com/paper/2602.18700/) (2026)
- [Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation](https://mlsanity.com/paper/2602.04195/) (2026)
- [Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy](https://mlsanity.com/paper/2405.02828/) (2024)
- [CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification](https://mlsanity.com/paper/2410.20136/) (2024)
- [Measuring Impacts of Poisoning on Model Parameters and Neuron Activations: A Case Study of Poisoning CodeBERT](https://mlsanity.com/paper/2402.12936/) (2024)
- [Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond](https://mlsanity.com/paper/2410.18114/) (2024)
- [Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution](https://mlsanity.com/paper/2508.21004/) (2025)
- [SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents](https://mlsanity.com/paper/2606.13757/) (2026)
- [Signature in Code Backdoor Detection, how far are we?](https://mlsanity.com/paper/2510.13992/) (2025)
- [Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models](https://mlsanity.com/paper/2606.10846/) (2026)
- [Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks](https://mlsanity.com/paper/2608.05659/) (2026)
- [Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities](https://mlsanity.com/paper/2609.15963/) (2026)

## Abstract (arXiv)

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting the scope of attacks. Moreover, the majority of attacks for pre-trained models are designed for understanding tasks. In this paper, we propose task-agnostic backdoor attacks for code pre-trained models. Our backdoored model is pre-trained with two learning strategies (i.e., Poisoned Seq2Seq learning and token representation learning) to support the multi-target attack of downstream code understanding and generation tasks. During the deployment phase, the implanted backdoors in the victim models can be activated by the designed triggers to achieve the targeted attack. We evaluate our approach on two code understanding tasks and three code generation tasks over seven datasets. Extensive experiments demonstrate that our approach can effectively and stealthily attack code-related downstream tasks.