Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

• URL: http://arxiv.org/abs/2410.13910v1
• Date: Thu, 17 Oct 2024 00:13:31 GMT
• Title: Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
• Authors: Jinluan Yang, Anke Tang, Didi Zhu, Zhengyu Chen, Li Shen, Fei Wu,
• Abstract summary: We propose a novel Defense-Aware Merging (DAM) approach that simultaneously mitigates task interference and backdoor vulnerabilities. Compared to existing merging methods, DAM achieves a more favorable balance between performance and security, reducing the attack success rate by 2-10 percentage points.
• Score: 15.457992715866995
• License:
• Abstract: Model merging has gained significant attention as a cost-effective approach to integrate multiple single-task fine-tuned models into a unified one that can perform well on multiple tasks. However, existing model merging techniques primarily focus on resolving conflicts between task-specific models, they often overlook potential security threats, particularly the risk of backdoor attacks in the open-source model ecosystem. In this paper, we first investigate the vulnerabilities of existing model merging methods to backdoor attacks, identifying two critical challenges: backdoor succession and backdoor transfer. To address these issues, we propose a novel Defense-Aware Merging (DAM) approach that simultaneously mitigates task interference and backdoor vulnerabilities. Specifically, DAM employs a meta-learning-based optimization method with dual masks to identify a shared and safety-aware subspace for model merging. These masks are alternately optimized: the Task-Shared mask identifies common beneficial parameters across tasks, aiming to preserve task-specific knowledge while reducing interference, while the Backdoor-Detection mask isolates potentially harmful parameters to neutralize security threats. This dual-mask design allows us to carefully balance the preservation of useful knowledge and the removal of potential vulnerabilities. Compared to existing merging methods, DAM achieves a more favorable balance between performance and security, reducing the attack success rate by 2-10 percentage points while sacrificing only about 1% in accuracy. Furthermore, DAM exhibits robust performance and broad applicability across various types of backdoor attacks and the number of compromised models involved in the merging process. We will release the codes and models soon.

Related papers

• Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting [6.984396318800444]
  Diffusion models have been proven to be vulnerable to Membership Inference Attacks (MIAs) This paper introduces two novel and efficient approaches to protect diffusion models against MIAs.
  arXiv  Detail & Related papers  (2024-10-22T03:02:29Z)
• Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues [88.96201324719205]
  This study exposes the safety vulnerabilities of Large Language Models (LLMs) in multi-turn interactions. We introduce ActorAttack, a novel multi-turn attack method inspired by actor-network theory.
  arXiv  Detail & Related papers  (2024-10-14T16:41:49Z)
• BadMerging: Backdoor Attacks Against Model Merging [17.797688491548175]
  We introduce BadMerging, the first backdoor attack specifically designed for Model Merging (MM) BadMerging comprises a two-stage attack mechanism and a novel feature-interpolation-based loss to enhance the robustness of embedded backdoors. Our experiments show that BadMerging achieves remarkable attacks against various MM algorithms.
  arXiv  Detail & Related papers  (2024-08-14T08:19:23Z)
• 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)
• Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models [65.30406788716104]
  This work investigates the vulnerabilities of security-enhancing diffusion models. We demonstrate that these models are highly susceptible to DIFF2, a simple yet effective backdoor attack. Case studies show that DIFF2 can significantly reduce both post-purification and certified accuracy across benchmark datasets and models.
  arXiv  Detail & Related papers  (2024-06-14T02:39:43Z)
• Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge [17.3048898399324]
  democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. backdoor attacks, where hidden malicious behaviors are triggered by specific inputs, compromising natural language processing (NLP) system integrity and reliability. This paper suggests that merging a backdoored model with other homogeneous models can significantly remediate backdoor vulnerabilities.
  arXiv  Detail & Related papers  (2024-02-29T16:37:08Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)
• Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples [67.66153875643964]
  Backdoor attacks are serious security threats to machine learning models. In this paper, we explore the task of purifying a backdoored model using a small clean dataset. By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk.
  arXiv  Detail & Related papers  (2023-07-20T03:56:04Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• Multi-Task Models Adversarial Attacks [25.834775498006657]
  Multi-Task Learning involves developing a singular model, known as a multi-task model, to concurrently perform multiple tasks. The security of single-task models has been thoroughly studied, but multi-task models pose several critical security questions. This paper addresses these queries through detailed analysis and rigorous experimentation.
  arXiv  Detail & Related papers  (2023-05-20T03:07:43Z)

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.