Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models

• URL: http://arxiv.org/abs/2407.02716v1
• Date: Tue, 2 Jul 2024 23:48:43 GMT
• Title: Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models
• Authors: Xu Han, Linghao Jin, Xuezhe Ma, Xiaofeng Liu,
• Abstract summary: Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Many pre-training datasets are restricted by patient privacy concerns, potentially containing noise that can adversely affect downstream performance. We propose rectify adversarial noise (RAN) framework, a recipe designed to effectively defend adversarial attacks and rectify the influence of upstream noise during fine-tuning.
• Score: 25.33637232484219
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially containing noise that can adversely affect downstream performance. Moreover, the growing reliance on multi-modal generation exacerbates this issue because of its susceptibility to adversarial attacks. To investigate how VLMs trained on adversarial noisy data perform on downstream medical tasks, we first craft noisy upstream datasets using multi-modal adversarial attacks. Through our comprehensive analysis, we unveil that moderate noise enhances model robustness and transferability, but increasing noise levels negatively impact downstream task performance. To mitigate this issue, we propose rectify adversarial noise (RAN) framework, a recipe designed to effectively defend adversarial attacks and rectify the influence of upstream noise during fine-tuning.

Related papers

• Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation [25.410770364140856]
  Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain. This study puts forward a novel data simulation method to address this issue, leveraging noise-extractive techniques and generative adversarial networks (GANs) We introduce the notion of dynamic perturbation, which can inject controlled perturbations into the noise embeddings during inference.
  arXiv  Detail & Related papers  (2024-09-03T02:29:01Z)
• ROPO: Robust Preference Optimization for Large Language Models [59.10763211091664]
  We propose an iterative alignment approach that integrates noise-tolerance and filtering of noisy samples without the aid of external models. Experiments on three widely-used datasets with Mistral-7B and Llama-2-7B demonstrate that ROPO significantly outperforms existing preference alignment methods.
  arXiv  Detail & Related papers  (2024-04-05T13:58:51Z)
• Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task [14.707646721729228]
  In a realistic dialogue system, the input information from users is often subject to various types of input perturbations. We propose Noise-BERT, a unified Perturbation-Robust Framework with Noise Alignment Pre-training. Our framework incorporates two Noise Alignment Pre-training tasks: Slot Masked Prediction and Sentence Noisiness Discrimination.
  arXiv  Detail & Related papers  (2024-02-22T12:39:50Z)
• Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise [31.586389548657205]
  Unlearnable example is proposed to significantly degrade the generalization performance of models by adding a kind of imperceptible noise to the data. We introduce stable error-minimizing noise (SEM), which trains the defensive noise against random perturbation instead of the time-consuming adversarial perturbation. SEM achieves a new state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet Subset.
  arXiv  Detail & Related papers  (2023-11-22T01:43:57Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• On enhancing the robustness of Vision Transformers: Defensive Diffusion [0.0]
  ViTs, the SOTA vision model, rely on large amounts of patient data for training. Adversaries may exploit vulnerabilities in ViTs to extract sensitive patient information and compromising patient privacy. This work addresses these vulnerabilities to ensure the trustworthiness and reliability of ViTs in medical applications.
  arXiv  Detail & Related papers  (2023-05-14T00:17:33Z)
• Treatment Learning Causal Transformer for Noisy Image Classification [62.639851972495094]
  In this work, we incorporate this binary information of "existence of noise" as treatment into image classification tasks to improve prediction accuracy. Motivated from causal variational inference, we propose a transformer-based architecture, that uses a latent generative model to estimate robust feature representations for noise image classification. We also create new noisy image datasets incorporating a wide range of noise factors for performance benchmarking.
  arXiv  Detail & Related papers  (2022-03-29T13:07:53Z)
• Towards Adversarially Robust Deep Image Denoising [199.2458715635285]
  This work systematically investigates the adversarial robustness of deep image denoisers (DIDs) We propose a novel adversarial attack, namely Observation-based Zero-mean Attack (sc ObsAtk) to craft adversarial zero-mean perturbations on given noisy images. To robustify DIDs, we propose hybrid adversarial training (sc HAT) that jointly trains DIDs with adversarial and non-adversarial noisy data.
  arXiv  Detail & Related papers  (2022-01-12T10:23:14Z)
• Removing Adversarial Noise in Class Activation Feature Space [160.78488162713498]
  We propose to remove adversarial noise by implementing a self-supervised adversarial training mechanism in a class activation feature space. We train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space. Empirical evaluations demonstrate that our method could significantly enhance adversarial robustness in comparison to previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-04-19T10:42:24Z)
• On Dynamic Noise Influence in Differentially Private Learning [102.6791870228147]
  Private Gradient Descent (PGD) is a commonly used private learning framework, which noises based on the Differential protocol. Recent studies show that emphdynamic privacy schedules can improve at the final iteration, yet yet theoreticals of the effectiveness of such schedules remain limited. This paper provides comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.
  arXiv  Detail & Related papers  (2021-01-19T02:04:00Z)

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.