Eliminating Backdoors in Neural Code Models for Secure Code Understanding

• URL: http://arxiv.org/abs/2408.04683v2
• Date: Thu, 20 Feb 2025 06:07:08 GMT
• Title: Eliminating Backdoors in Neural Code Models for Secure Code Understanding
• Authors: Weisong Sun, Yuchen Chen, Chunrong Fang, Yebo Feng, Yuan Xiao, An Guo, Quanjun Zhang, Yang Liu, Baowen Xu, Zhenyu Chen,
• Abstract summary: Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. Backdoored NCMs function normally on normal/clean code snippets, but exhibit adversary-expected behavior on poisoned code snippets. We propose EliBadCode to eliminate backdoors in NCMs by inverting/reverse-engineering and unlearning backdoor triggers.
• Score: 24.053091055319562
• License:
• Abstract: Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function normally on normal/clean code snippets, but exhibit adversary-expected behavior on poisoned code snippets injected with the adversary-crafted trigger. It poses a significant security threat. Therefore, there is an urgent need for effective techniques to detect and eliminate backdoors stealthily implanted in NCMs. To address this issue, in this paper, we innovatively propose a backdoor elimination technique for secure code understanding, called EliBadCode. EliBadCode eliminates backdoors in NCMs by inverting/reverse-engineering and unlearning backdoor triggers. Specifically, EliBadCode first filters the model vocabulary for trigger tokens based on the naming conventions of specific programming languages to reduce the trigger search space and cost. Then, EliBadCode introduces a sample-specific trigger position identification method, which can reduce the interference of non-backdoor (adversarial) perturbations for subsequent trigger inversion, thereby producing effective inverted backdoor triggers efficiently. Backdoor triggers can be viewed as backdoor (adversarial) perturbations. Subsequently, EliBadCode employs a Greedy Coordinate Gradient algorithm to optimize the inverted trigger and designs a trigger anchoring method to purify the inverted trigger. Finally, EliBadCode eliminates backdoors through model unlearning. We evaluate the effectiveness of EliBadCode in eliminating backdoors implanted in multiple NCMs used for three safety-critical code understanding tasks. The results demonstrate that EliBadCode can effectively eliminate backdoors while having minimal adverse effects on the normal functionality of the model.

Related papers

• CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification [19.570958294967536]
  backdoor attacks can achieve nearly 100% attack success rates on many software engineering tasks. We propose CodePurify, a novel defense against backdoor attacks on code models through entropy-based purification. We extensively evaluate CodePurify against four advanced backdoor attacks across three representative tasks and two popular code models.
  arXiv  Detail & Related papers  (2024-10-26T10:17:50Z)
• "No Matter What You Do": Purifying GNN Models via Backdoor Unlearning [33.07926413485209]
  backdoor attacks in GNNs lie in the fact that the attacker modifies a portion of graph data by embedding triggers. We present GCleaner, the first backdoor mitigation method on GNNs. GCleaner can reduce the backdoor attack success rate to 10% with only 1% of clean data, and has almost negligible degradation in model performance.
  arXiv  Detail & Related papers  (2024-10-02T06:30:49Z)
• BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models [57.5404308854535]
  Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations.
  arXiv  Detail & Related papers  (2024-06-24T19:29:47Z)
• Backdoor Attack with Sparse and Invisible Trigger [57.41876708712008]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. backdoor attack is an emerging yet threatening training-phase threat. We propose a sparse and invisible backdoor attack (SIBA)
  arXiv  Detail & Related papers  (2023-05-11T10:05:57Z)
• UNICORN: A Unified Backdoor Trigger Inversion Framework [13.841110859970827]
  Trigger inversion is an effective way of identifying backdoor models and understanding embedded adversarial behaviors. This work formally defines and analyzes the triggers injected in different spaces and the inversion problem. Then, it proposes a unified framework to invert backdoor triggers based on the formalization of triggers and the identified inner behaviors of backdoor models.
  arXiv  Detail & Related papers  (2023-04-05T23:14:08Z)
• Backdoor Attacks with Input-unique Triggers in NLP [34.98477726215485]
  Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged. In this paper, we propose an input-unique backdoor attack(NURA), where we generate backdoor triggers unique to inputs.
  arXiv  Detail & Related papers  (2023-03-25T01:41:54Z)
• Stealthy Backdoor Attack for Code Models [19.272856932095966]
  Existing backdoor attacks on code models use unstealthy and easy-to-detect triggers. This paper aims to investigate the vulnerability of code models with stealthy backdoor attacks. We find that around 85% of adaptive triggers in AFRAIDOOR bypass the detection in the defense process.
  arXiv  Detail & Related papers  (2023-01-06T13:15:42Z)
• Backdoor Defense via Suppressing Model Shortcuts [91.30995749139012]
  In this paper, we explore the backdoor mechanism from the angle of the model structure. We demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections.
  arXiv  Detail & Related papers  (2022-11-02T15:39:19Z)
• Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution [57.51117978504175]
  Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is activated. We present invisible backdoors that are activated by a learnable combination of word substitution.
  arXiv  Detail & Related papers  (2021-06-11T13:03:17Z)
• Black-box Detection of Backdoor Attacks with Limited Information and Data [56.0735480850555]
  We propose a black-box backdoor detection (B3D) method to identify backdoor attacks with only query access to the model. In addition to backdoor detection, we also propose a simple strategy for reliable predictions using the identified backdoored models.
  arXiv  Detail & Related papers  (2021-03-24T12:06:40Z)
• Defending against Backdoor Attack on Deep Neural Networks [98.45955746226106]
  We study the so-called textitbackdoor attack, which injects a backdoor trigger to a small portion of training data. Experiments show that our method could effectively decrease the attack success rate, and also hold a high classification accuracy for clean images.
  arXiv  Detail & Related papers  (2020-02-26T02:03:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.