Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models

• URL: http://arxiv.org/abs/2501.03272v1
• Date: Sun, 05 Jan 2025 03:22:13 GMT
• Title: Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
• Authors: Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma,
• Abstract summary: We propose a novel defense method called Backdoor Token Unlearning (BTU), which proactively detects and neutralizes trigger tokens during the training stage. Our work is based on two key findings: 1) backdoor learning causes distinctive differences between backdoor token parameters and clean token parameters in word embedding layers, and 2) the success of backdoor attacks heavily depends on backdoor token parameters.
• Score: 9.995807326278959
• License:
• Abstract: Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of malicious samples can successfully embed backdoor triggers into the model. While most existing defense methods focus on post-training backdoor defense, efficiently defending against backdoor attacks during training phase remains largely unexplored. To address this gap, we propose a novel defense method called Backdoor Token Unlearning (BTU), which proactively detects and neutralizes trigger tokens during the training stage. Our work is based on two key findings: 1) backdoor learning causes distinctive differences between backdoor token parameters and clean token parameters in word embedding layers, and 2) the success of backdoor attacks heavily depends on backdoor token parameters. The BTU defense leverages these properties to identify aberrant embedding parameters and subsequently removes backdoor behaviors using a fine-grained unlearning technique. Extensive evaluations across three datasets and four types of backdoor attacks demonstrate that BTU effectively defends against these threats while preserving the model's performance on primary tasks. Our code is available at https://github.com/XDJPH/BTU.

Related papers

• Data Free Backdoor Attacks [83.10379074100453]
  DFBA is a retraining-free and data-free backdoor attack without changing the model architecture. We verify that our injected backdoor is provably undetectable and unchosen by various state-of-the-art defenses. Our evaluation on multiple datasets demonstrates that our injected backdoor: 1) incurs negligible classification loss, 2) achieves 100% attack success rates, and 3) bypasses six existing state-of-the-art defenses.
  arXiv  Detail & Related papers  (2024-12-09T05:30:25Z)
• Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models [6.937795040660591]
  We introduce Deferred Activated Backdoor Functionality (DABF) as a new paradigm in backdoor attacks. Unlike conventional attacks, DABF initially conceals its backdoor, producing benign outputs even when triggered. DABF attacks exploit the common practice in the life cycle of machine learning models to perform model updates and fine-tuning after initial deployment.
  arXiv  Detail & Related papers  (2024-11-10T07:01:53Z)
• Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models [68.40324627475499]
  We introduce a novel two-step defense framework named Expose Before You Defend. EBYD unifies existing backdoor defense methods into a comprehensive defense system with enhanced performance. We conduct extensive experiments on 10 image attacks and 6 text attacks across 2 vision datasets and 4 language datasets.
  arXiv  Detail & Related papers  (2024-10-25T09:36:04Z)
• Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation [10.888542040021962]
  W2SDefense is a weak-to-strong unlearning algorithm to defend against backdoor attacks. We conduct experiments on text classification tasks involving three state-of-the-art language models and three different backdoor attack algorithms.
  arXiv  Detail & Related papers  (2024-10-18T12:39:32Z)
• Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats [52.94388672185062]
  We propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime.
  arXiv  Detail & Related papers  (2024-09-29T02:55:38Z)
• Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor [63.84477483795964]
  Data-poisoning backdoor attacks are serious security threats to machine learning models. In this paper, we focus on in-training backdoor defense, aiming to train a clean model even when the dataset may be potentially poisoned. We propose a novel defense approach called PDB (Proactive Defensive Backdoor)
  arXiv  Detail & Related papers  (2024-05-25T07:52:26Z)
• Rethinking Backdoor Attacks [122.1008188058615]
  In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted examples as outliers in the training set and using techniques from robust statistics to detect and remove them. We show that without structural information about the training data distribution, backdoor attacks are indistinguishable from naturally-occurring features in the data.
  arXiv  Detail & Related papers  (2023-07-19T17:44:54Z)
• Anti-Backdoor Learning: Training Clean Models on Poisoned Data [17.648453598314795]
  Backdoor attack has emerged as a major security threat to deep neural networks (DNNs) We introduce the concept of emphanti-backdoor learning, aiming to train emphclean models given backdoor-poisoned data. We empirically show that ABL-trained models on backdoor-poisoned data achieve the same performance as they were trained on purely clean data.
  arXiv  Detail & Related papers  (2021-10-22T03:30:48Z)
• Backdoor Learning: A Survey [75.59571756777342]
  Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs) Backdoor learning is an emerging and rapidly growing research area. This paper presents the first comprehensive survey of this realm.
  arXiv  Detail & Related papers  (2020-07-17T04:09:20Z)

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.