The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels

• URL: http://arxiv.org/abs/2410.10473v4
• Date: Wed, 15 Oct 2025 09:56:23 GMT
• Title: The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
• Abstract summary: Prior work argued that the implicit bias of structured state space models (SSMs) leads to generalization in a setting where data is generated by a low dimensional teacher.<n>We prove that while implicit bias leads to generalization under many choices of training data, there exist special examples whose inclusion in training completely distorts the implicit bias.<n>This failure occurs despite the special training examples being labeled by the teacher, i.e. having clean labels!
• Score: 8.670973157365689
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data. A recent class of neural network models gaining increasing popularity is structured state space models (SSMs), regarded as an efficient alternative to transformers. Prior work argued that the implicit bias of SSMs leads to generalization in a setting where data is generated by a low dimensional teacher. In this paper, we revisit the latter setting, and formally establish a phenomenon entirely undetected by prior work on the implicit bias of SSMs. Namely, we prove that while implicit bias leads to generalization under many choices of training data, there exist special examples whose inclusion in training completely distorts the implicit bias, to a point where generalization fails. This failure occurs despite the special training examples being labeled by the teacher, i.e. having clean labels! We empirically demonstrate the phenomenon, with SSMs trained independently and as part of non-linear neural networks. In the area of adversarial machine learning, disrupting generalization with cleanly labeled training examples is known as clean-label poisoning. Given the proliferation of SSMs, we believe that delineating their susceptibility to clean-label poisoning, and developing methods for overcoming this susceptibility, are critical research directions to pursue.

Related papers

• On the Dynamics & Transferability of Latent Generalization during Memorization [0.0]
  We study the origin and dynamics over training of latent generalization abilities during memorization.<n>We find that latent generalization abilities largely peak early in training, with model generalization.<n>We devise a way to transfer the latent generalization present in last-layer representations to the model using a new linear probe.
  arXiv  Detail & Related papers  (2026-03-20T11:30:57Z)
• KnowBias: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement [5.243877326529689]
  Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment.<n>We propose KnowBias, a framework that mitigates bias by strengthening, rather than suppressing, neurons encoding bias-knowledge.<n>KnowBias identifies neurons encoding bias knowledge using a small set of bias-knowledge questions via attribution-based analysis, and selectively enhances them at inference time.
  arXiv  Detail & Related papers  (2026-01-29T15:32:38Z)
• How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
  This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs.<n>Our findings reveal that biases present in pre-training data are amplified in model outputs.
  arXiv  Detail & Related papers  (2024-11-28T16:20:25Z)
• Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective [6.164100243945264]
  Semi-supervised learning (SSL) commonly exhibits confirmation bias, where models disproportionately favor certain classes. We introduce TaMatch, a unified framework for debiased training in SSL. We show that TaMatch significantly outperforms existing state-of-the-art methods across a range of challenging image classification tasks.
  arXiv  Detail & Related papers  (2024-09-26T21:50:30Z)
• Model Debiasing by Learnable Data Augmentation [19.625915578646758]
  This paper proposes a novel 2-stage learning pipeline featuring a data augmentation strategy able to regularize the training. Experiments on synthetic and realistic biased datasets show state-of-the-art classification accuracy, outperforming competing methods.
  arXiv  Detail & Related papers  (2024-08-09T09:19:59Z)
• The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models [78.69526166193236]
  Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases. We propose sc Social Bias Neurons to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost.
  arXiv  Detail & Related papers  (2024-06-14T15:41:06Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• Self-supervised debiasing using low rank regularization [59.84695042540525]
  Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. We propose a self-supervised debiasing framework potentially compatible with unlabeled samples. Remarkably, the proposed debiasing framework significantly improves the generalization performance of self-supervised learning baselines.
  arXiv  Detail & Related papers  (2022-10-11T08:26:19Z)
• Unsupervised Learning of Unbiased Visual Representations [10.871587311621974]
  Deep neural networks are known for their inability to learn robust representations when biases exist in the dataset. We propose a fully unsupervised debiasing framework, consisting of three steps. We employ state-of-the-art supervised debiasing techniques to obtain an unbiased model.
  arXiv  Detail & Related papers  (2022-04-26T10:51:50Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization [93.8373619657239]
  Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features. This simplicity bias can explain their lack of robustness out of distribution (OOD) We demonstrate that the simplicity bias can be mitigated and OOD generalization improved.
  arXiv  Detail & Related papers  (2021-05-12T12:12:24Z)
• Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer [72.5190560787569]
  In computer vision, learning from long tailed datasets is a recurring theme, especially for natural image datasets. Our proposal posits a meta-distributional scenario, where the data generating mechanism is invariant across the label-conditional feature distributions. This allows us to leverage a causal data inflation procedure to enlarge the representation of minority classes.
  arXiv  Detail & Related papers  (2020-11-25T00:13:11Z)
• Learning from Failure: Training Debiased Classifier from Biased Classifier [76.52804102765931]
  We show that neural networks learn to rely on spurious correlation only when it is "easier" to learn than the desired knowledge. We propose a failure-based debiasing scheme by training a pair of neural networks simultaneously. Our method significantly improves the training of the network against various types of biases in both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2020-07-06T07:20:29Z)

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.