Partially Recentralization Softmax Loss for Vision-Language Models Robustness

• URL: http://arxiv.org/abs/2402.03627v2
• Date: Tue, 08 Oct 2024 08:13:25 GMT
• Title: Partially Recentralization Softmax Loss for Vision-Language Models Robustness
• Authors: Hao Wang, Jinzhe Jiang, Xin Zhang, Chen Li,
• Abstract summary: We study the adversarial robustness provided by modifying loss function of pre-trained multimodal models. Our experiments show that after a fine-tuning, adversarial robustness of pre-trained models can be significantly improved, against popular attacks.
• Score: 8.78222772167501
• License:
• Abstract: As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs of a model can be dramatically changed by a perturbation to the input. While several defense techniques have been proposed both in computer vision and NLP models, the multimodal robustness of models have not been fully explored. In this paper, we study the adversarial robustness provided by modifying loss function of pre-trained multimodal models, by restricting top K softmax outputs. Based on the evaluation and scoring, our experiments show that after a fine-tuning, adversarial robustness of pre-trained models can be significantly improved, against popular attacks. Further research should be studying, such as output diversity, generalization and the robustness-performance trade-off of this kind of loss functions. Our code will be available after this paper is accepted

Related papers

• MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models [30.04163729936878]
  Meticulous Adrial Attack (MAA) fully exploit model-independent characteristics and vulnerabilities of individual samples. MAA emphasizes fine-grained optimization of adversarial images by developing a novel resizing and sliding crop (RScrop) technique.
  arXiv  Detail & Related papers  (2025-02-12T02:53:27Z)
• Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models [26.656858396343726]
  Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations. Existing methods seek to mitigate these risks by applying constrained adversarial fine-tuning to CLIP vision encoders on ImageNet-scale data. We explore an alternative approach of leveraging existing vision classification models that have been adversarially pre-trained on large-scale data.
  arXiv  Detail & Related papers  (2025-02-03T17:59:45Z)
• RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models [60.596005921295806]
  Agglomerative models have emerged as a powerful approach to training vision foundation models. We identify critical challenges including resolution mode shifts, teacher imbalance, idiosyncratic teacher artifacts, and an excessive number of output tokens. We propose several novel solutions: multi-resolution training, mosaic augmentation, and improved balancing of teacher loss functions.
  arXiv  Detail & Related papers  (2024-12-10T17:06:41Z)
• Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality [69.76121008898677]
  Fine-grained Selective Calibrated CLIP integrates local hard negative loss and selective calibrated regularization. Our evaluations show that FSC-CLIP not only achieves compositionality on par with state-of-the-art models but also retains strong multi-modal capabilities.
  arXiv  Detail & Related papers  (2024-10-07T17:16:20Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models [34.802736332993994]
  We propose MMCert, the first certified defense against adversarial attacks to a multi-modal model. We evaluate our MMCert using two benchmark datasets: one for the multi-modal road segmentation task and the other for the multi-modal emotion recognition task.
  arXiv  Detail & Related papers  (2024-03-28T01:05:06Z)
• Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets [46.19529338280716]
  Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations. We introduce a methodology designed to examine how input perturbations affect language models across various scales. We present three distinct fine-tuning strategies to address robustness against multiple perturbations.
  arXiv  Detail & Related papers  (2023-11-15T02:59:10Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Tailoring Language Generation Models under Total Variation Distance [55.89964205594829]
  The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. We develop practical bounds to apply it to language generation. We introduce the TaiLr objective that balances the tradeoff of estimating TVD.
  arXiv  Detail & Related papers  (2023-02-26T16:32:52Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)

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.