BadMerging: Backdoor Attacks Against Model Merging

• URL: http://arxiv.org/abs/2408.07362v2
• Date: Mon, 2 Sep 2024 08:28:44 GMT
• Title: BadMerging: Backdoor Attacks Against Model Merging
• Authors: Jinghuai Zhang, Jianfeng Chi, Zheng Li, Kunlin Cai, Yang Zhang, Yuan Tian,
• Abstract summary: 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.
• Score: 17.797688491548175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these independently fine-tuned models. MM directly combines multiple fine-tuned task-specific models into a merged model without additional training, and the resulting model shows enhanced capabilities in multiple tasks. Although MM provides great utility, it may come with security risks because an adversary can exploit MM to affect multiple downstream tasks. However, the security risks of MM have barely been studied. In this paper, we first find that MM, as a new learning paradigm, introduces unique challenges for existing backdoor attacks due to the merging process. To address these challenges, we introduce BadMerging, the first backdoor attack specifically designed for MM. Notably, BadMerging allows an adversary to compromise the entire merged model by contributing as few as one backdoored task-specific model. BadMerging comprises a two-stage attack mechanism and a novel feature-interpolation-based loss to enhance the robustness of embedded backdoors against the changes of different merging parameters. Considering that a merged model may incorporate tasks from different domains, BadMerging can jointly compromise the tasks provided by the adversary (on-task attack) and other contributors (off-task attack) and solve the corresponding unique challenges with novel attack designs. Extensive experiments show that BadMerging achieves remarkable attacks against various MM algorithms. Our ablation study demonstrates that the proposed attack designs can progressively contribute to the attack performance. Finally, we show that prior defense mechanisms fail to defend against our attacks, highlighting the need for more advanced defense.

Related papers

• Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace [15.457992715866995]
  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.
  arXiv  Detail & Related papers  (2024-10-17T00:13:31Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• 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)
• On the Robustness of Large Multimodal Models Against Image Adversarial Attacks [81.2935966933355]
  We study the impact of visual adversarial attacks on Large Multimodal Models (LMMs) We find that in general LMMs are not robust to visual adversarial inputs. We propose a new approach to real-world image classification which we term query decomposition.
  arXiv  Detail & Related papers  (2023-12-06T04:59:56Z)
• AdaMerging: Adaptive Model Merging for Multi-Task Learning [68.75885518081357]
  This paper introduces an innovative technique called Adaptive Model Merging (AdaMerging) It aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data. Compared to the current state-of-the-art task arithmetic merging scheme, AdaMerging showcases a remarkable 11% improvement in performance.
  arXiv  Detail & Related papers  (2023-10-04T04:26:33Z)
• 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)
• 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)
• Defending Variational Autoencoders from Adversarial Attacks with MCMC [74.36233246536459]
  Variational autoencoders (VAEs) are deep generative models used in various domains. As previous work has shown, one can easily fool VAEs to produce unexpected latent representations and reconstructions for a visually slightly modified input. Here, we examine several objective functions for adversarial attacks construction, suggest metrics assess the model robustness, and propose a solution.
  arXiv  Detail & Related papers  (2022-03-18T13:25:18Z)
• Training Meta-Surrogate Model for Transferable Adversarial Attack [98.13178217557193]
  We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversarial examples to fool the target model. We show we can obtain a Meta-Surrogate Model (MSM) such that attacks to this model can be easier transferred to other models.
  arXiv  Detail & Related papers  (2021-09-05T03:27:46Z)

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.