Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications

• URL: http://arxiv.org/abs/2305.06522v1
• Date: Thu, 11 May 2023 01:50:16 GMT
• Title: Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications
• Authors: Han Cheol Moon, Shafiq Joty, Ruochen Zhao, Megh Thakkar, Xu Chi
• Abstract summary: We introduce RSMI, a novel two-stage framework that combines randomized smoothing (RS) with masked inference (MI) to improve the adversarial robustness of NLP systems. RS transforms a classifier into a smoothed classifier to obtain robust representations, whereas MI forces a model to exploit the surrounding context of a masked token in an input sequence. RSMI improves adversarial robustness by 2 to 3 times over existing state-of-the-art methods on benchmark datasets.
• Score: 3.6048665052465667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale pre-trained language models have shown outstanding performance in a variety of NLP tasks. However, they are also known to be significantly brittle against specifically crafted adversarial examples, leading to increasing interest in probing the adversarial robustness of NLP systems. We introduce RSMI, a novel two-stage framework that combines randomized smoothing (RS) with masked inference (MI) to improve the adversarial robustness of NLP systems. RS transforms a classifier into a smoothed classifier to obtain robust representations, whereas MI forces a model to exploit the surrounding context of a masked token in an input sequence. RSMI improves adversarial robustness by 2 to 3 times over existing state-of-the-art methods on benchmark datasets. We also perform in-depth qualitative analysis to validate the effectiveness of the different stages of RSMI and probe the impact of its components through extensive ablations. By empirically proving the stability of RSMI, we put it forward as a practical method to robustly train large-scale NLP models. Our code and datasets are available at https://github.com/Han8931/rsmi_nlp

Related papers

• RefiDiff: Refinement-Aware Diffusion for Efficient Missing Data Imputation [13.401822039640297]
  Missing values in high-dimensional, mixed-type datasets pose significant challenges for data imputation.<n>We propose an innovative framework, RefiDiff, combining local machine learning predictions with a novel Mamba-based denoising network.<n>RefiDiff outperforms state-the-art (SOTA) methods across missing-value settings with a 4x faster training time than DDPM-based approaches.
  arXiv  Detail & Related papers  (2025-05-20T14:51:07Z)
• Random-Set Large Language Models [4.308457163593758]
  Large Language Models (LLMs) are known to produce very high-quality tests and responses to our queries. But how much can we trust this generated text? We propose a novel Random-Set Large Language Model (RSLLM) approach which predicts finite random sets (belief functions) over the token space.
  arXiv  Detail & Related papers  (2025-04-25T05:25:27Z)
• Harnessing Mixed Features for Imbalance Data Oversampling: Application to Bank Customers Scoring [5.091061468748012]
  We introduce MGS-GRF, an oversampling strategy designed for mixed features. We show that MGS-GRF exhibits two important properties: (i) the coherence i.e. the ability to only generate combinations of categorical features that are already present in the original dataset and (ii) association, i.e. the ability to preserve the dependence between continuous and categorical features.
  arXiv  Detail & Related papers  (2025-03-26T08:53:40Z)
• Certainly Bot Or Not? Trustworthy Social Bot Detection via Robust Multi-Modal Neural Processes [28.951832771823128]
  Social bot detection is crucial for mitigating misinformation, online manipulation, and coordinated inauthentic behavior. Existing neural network-based detectors struggle with generalization due to distribution shifts across datasets. We introduce a novel Uncertainty Estimation for Social Bot Detection framework, which quantifies the predictive uncertainty of detectors beyond mere classification.
  arXiv  Detail & Related papers  (2025-03-11T01:32:52Z)
• Ensemble Methods for Sequence Classification with Hidden Markov Models [8.241486511994202]
  We present a lightweight approach to sequence classification using Ensemble Methods for Hidden Markov Models (HMMs) HMMs offer significant advantages in scenarios with imbalanced or smaller datasets due to their simplicity, interpretability, and efficiency. Our ensemble-based scoring method enables the comparison of sequences of any length and improves performance on imbalanced datasets.
  arXiv  Detail & Related papers  (2024-09-11T20:59:32Z)
• Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter [32.64004722423187]
  We show how to improve the robustness of RGB-skeleton action recognition models. We propose the formatwordAttention-based formatwordModality formatwordReweighter (formatwordAMR) Our AMR is plug-and-play, allowing easy integration with multimodal models.
  arXiv  Detail & Related papers  (2024-07-29T13:15:51Z)
• MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization [49.00754561435518]
  MSRS achieves competitive results in VSR and AVSR with 21.1% and 0.9% WER on the LRS3 benchmark, while reducing training time by at least 2x. We explore other sparse approaches and show that only MSRS enables training from scratch by implicitly masking the weights affected by vanishing gradients.
  arXiv  Detail & Related papers  (2024-06-25T15:00:43Z)
• 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)
• Soft Random Sampling: A Theoretical and Empirical Analysis [59.719035355483875]
  Soft random sampling (SRS) is a simple yet effective approach for efficient deep neural networks when dealing with massive data. It selects a uniformly speed at random with replacement from each data set in each epoch. It is shown to be a powerful and competitive strategy with significant and competitive performance on real-world industrial scale.
  arXiv  Detail & Related papers  (2023-11-21T17:03:21Z)
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding [38.11411155621616]
  We study self-training as one of the predominant semi-supervised learning approaches. We present UPET, a novel Uncertainty-aware self-Training framework. We show that UPET achieves a substantial improvement in terms of performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-19T02:18:29Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning [3.775565013663731]
  We propose a new method -- Sparser Random Feature Models via IMP (ShRIMP) -- to efficiently fit high-dimensional data with inherent low-dimensional structure. Our method can be viewed as a combined process to construct and find sparse lottery tickets for two-layer dense networks.
  arXiv  Detail & Related papers  (2021-12-07T21:32:28Z)
• Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble [163.3333439344695]
  Dirichlet Neighborhood Ensemble (DNE) is a randomized smoothing method for training a robust model to defense substitution-based attacks. DNE forms virtual sentences by sampling embedding vectors for each word in an input sentence from a convex hull spanned by the word and its synonyms, and it augments them with the training data. We demonstrate through extensive experimentation that our method consistently outperforms recently proposed defense methods by a significant margin across different network architectures and multiple data sets.
  arXiv  Detail & Related papers  (2020-06-20T18:01:16Z)
• Learning to Learn Kernels with Variational Random Features [118.09565227041844]
  We introduce kernels with random Fourier features in the meta-learning framework to leverage their strong few-shot learning ability. We formulate the optimization of MetaVRF as a variational inference problem. We show that MetaVRF delivers much better, or at least competitive, performance compared to existing meta-learning alternatives.
  arXiv  Detail & Related papers  (2020-06-11T18:05:29Z)

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.