Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging

• URL: http://arxiv.org/abs/2502.16094v1
• Date: Sat, 22 Feb 2025 05:34:53 GMT
• Title: Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging
• Authors: Lin Lu, Zhigang Zuo, Ziji Sheng, Pan Zhou,
• Abstract summary: We propose textttMerger-as-a-Stealer, a two-stage framework to achieve this attack.<n>First, the attacker fine-tunes a malicious model to force it to respond to any PII-related queries.<n>Second, the attacker inputs direct PII-related queries to the merged model to extract targeted PII.
• Score: 49.270050440553575
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model merging has emerged as a promising approach for updating large language models (LLMs) by integrating multiple domain-specific models into a cross-domain merged model. Despite its utility and plug-and-play nature, unmonitored mergers can introduce significant security vulnerabilities, such as backdoor attacks and model merging abuse. In this paper, we identify a novel and more realistic attack surface where a malicious merger can extract targeted personally identifiable information (PII) from an aligned model with model merging. Specifically, we propose \texttt{Merger-as-a-Stealer}, a two-stage framework to achieve this attack: First, the attacker fine-tunes a malicious model to force it to respond to any PII-related queries. The attacker then uploads this malicious model to the model merging conductor and obtains the merged model. Second, the attacker inputs direct PII-related queries to the merged model to extract targeted PII. Extensive experiments demonstrate that \texttt{Merger-as-a-Stealer} successfully executes attacks against various LLMs and model merging methods across diverse settings, highlighting the effectiveness of the proposed framework. Given that this attack enables character-level extraction for targeted PII without requiring any additional knowledge from the attacker, we stress the necessity for improved model alignment and more robust defense mechanisms to mitigate such threats.

Related papers

• Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy [0.0]
  Model merging is a technique that combines multiple finetuned models into a single model without additional training. Existing methods such as model watermarking or fingerprinting can only detect merging in hindsight. We propose a first proactive defense against model merging.
  arXiv  Detail & Related papers  (2025-03-08T06:08:47Z)
• Zero-Trust Artificial Intelligence Model Security Based on Moving Target Defense and Content Disarm and Reconstruction [4.0208298639821525]
  This paper examines the challenges in distributing AI models through model zoos and file transfer mechanisms. The physical security of model files is critical, requiring stringent access controls and attack prevention solutions. It demonstrates a 100% disarm rate while validated against known AI model repositories and actual malware attacks from the HuggingFace model zoo.
  arXiv  Detail & Related papers  (2025-03-03T17:32:19Z)
• LoBAM: LoRA-Based Backdoor Attack on Model Merging [27.57659381949931]
  Model merging is an emerging technique that integrates multiple models fine-tuned on different tasks to create a versatile model that excels in multiple domains.<n>Existing works try to demonstrate the risk of such attacks by assuming substantial computational resources.<n>We propose LoBAM, a method that yields high attack success rate with minimal training resources.
  arXiv  Detail & Related papers  (2024-11-23T20:41:24Z)
• Model Merging and Safety Alignment: One Bad Model Spoils the Bunch [70.614652904151]
  Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model. Current approaches often overlook the importance of safety alignment during merging, leading to highly misaligned models. We evaluate several popular model merging techniques, demonstrating that existing methods do not only transfer domain expertise but also propagate misalignment.
  arXiv  Detail & Related papers  (2024-06-20T17:59:58Z)
• 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)
• Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging [25.327483618051378]
  We conduct the first study on the robustness of IP protection methods under model merging scenarios. Experimental results indicate that current Large Language Model (LLM) watermarking techniques cannot survive in the merged models. Our research aims to highlight that model merging should be an indispensable consideration in the robustness assessment of model IP protection techniques.
  arXiv  Detail & Related papers  (2024-04-08T04:30:33Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model [14.834360664780709]
  Model attacks (MIAs) aim to recover private data from inaccessible training sets of deep learning models. This paper develops a novel MIA method, leveraging a conditional diffusion model (CDM) to recover representative samples under the target label. Experimental results show that this method can generate similar and accurate samples to the target label, outperforming generators of previous approaches.
  arXiv  Detail & Related papers  (2023-07-17T12:14:24Z)
• 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)
• Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution [83.02632136860976]
  We study black-box adversarial attacks against deep neural networks (DNNs) We develop a novel mechanism of adversarial transferability, which is robust to the surrogate biases. Experiments on benchmark datasets and attacking against real-world API demonstrate the superior attack performance of the proposed method.
  arXiv  Detail & Related papers  (2020-06-15T16:45:27Z)

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.