Robustness Verification of Recurrent Neural Networks with Abstraction Refinement

• URL: http://arxiv.org/abs/2606.12490v1
• Date: Wed, 10 Jun 2026 11:30:37 GMT
• Title: Robustness Verification of Recurrent Neural Networks with Abstraction Refinement
• Abstract summary: We propose an abstraction-refinement framework for RNN verification that partitions such intervals to remove the dominant relaxation error.<n>Experiments on CIFAR10 and MNIST stroke benchmarks demonstrate consistent improvements in verification success and robustness-margin tightness over abstraction-only baselines.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Certified local robustness verification for recurrent neural networks (RNNs) is challenging because approximation errors introduced by nonlinear relaxations can propagate through recurrent connections and accumulate over time. As a result, scalable linear bound propagation methods often become overly conservative and fail to certify inputs that are in fact robust, especially when many pre-activation intervals cross zero. We propose an abstraction-refinement framework for RNN verification that partitions such intervals to remove the dominant relaxation error: on each refined branch, ReLU becomes exact, and smooth activations such as tanh and sigmoid admit substantially tighter linear envelopes. To control the combinatorial cost of splitting in long sequences, we introduce a SHAP-guided timestep selection strategy that ranks hidden states by their contribution to the verification objective and refines only the most critical timesteps in temporal order. Experiments on CIFAR10 and MNIST stroke benchmarks demonstrate consistent improvements in verification success and robustness-margin tightness over abstraction-only baselines, while exposing clear runtime trade-offs between ReLU and tanh models.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation [50.139984798361375]
  We propose a training-free framework that removes redundancy via latent discrepancy.<n> LD-Pruning substantially reduces inference while maintaining high generation quality, achieving up to 2.35x speedup on Infinity-8B.
  arXiv  Detail & Related papers  (2026-05-29T19:34:39Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Improving Spatio-Temporal Residual Error Propagation by Mitigating Over-Squashing [4.62541204592513]
  We introduce Teger, a structured uncertainty module that overcomes the spa- tial and temporal limitations of error-related autoregressive forecasting.<n>Teger is backbone-agnostic, requiring only the latent state produced by any autoregressive encoder.
  arXiv  Detail & Related papers  (2026-05-18T08:51:33Z)
• Counterexample Guided Branching via Directional Relaxation Analysis in Complete Neural Network Verification [10.808953992870954]
  Deep Neural Networks demonstrate exceptional performance but remain vulnerable to adversarial perturbations.<n>Current dataflow approaches operate with blind refinement processes that rely on statics.<n>We propose DRG-BaB, a framework that introduces the Directional Gap to prioritize branching on neurons actively contributing to falsification.
  arXiv  Detail & Related papers  (2026-03-16T04:57:44Z)
• Error Amplification Limits ANN-to-SNN Conversion in Continuous Control [64.99656514469972]
  Spiking Neural Networks (SNNs) can achieve competitive performance by converting already existing well-trained Artificial Neural Networks (ANNs)<n>Existing conversion methods perform poorly in continuous control, where suitable baselines are largely absent.<n>We propose Cross-Step Residual Potential Initialization (CRPI), a lightweight training-free mechanism that carries over residual membrane potentials across decision steps to suppress temporally correlated errors.
  arXiv  Detail & Related papers  (2026-01-29T14:28:00Z)
• Lipschitz-Based Robustness Certification for Recurrent Neural Networks via Convex Relaxation [0.0]
  We present RNN-SDP, a relaxation based method that models the RNN's layer interactions as a convex problem.<n>We also explore an extension that incorporates known input constraints to further tighten the resulting Lipschitz bounds.
  arXiv  Detail & Related papers  (2025-09-22T15:26:46Z)
• Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks [2.1838661321884443]
  Recurrent Neural Networks (RNNs) are widely used for sequential processing but face limitations with continual inference due to state saturation.<n>We propose an adaptive loss function that eliminates the need for resets during inference while preserving high accuracy over extended sequences.
  arXiv  Detail & Related papers  (2024-12-20T15:24:28Z)
• IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound [85.6899802468343]
  We present IBP-R, a novel verified training algorithm that is both simple effective. We also present UPB, a novel robustness based on $beta$-CROWN, that reduces the cost state-of-the-art branching algorithms.
  arXiv  Detail & Related papers  (2022-06-29T17:13:25Z)
• Can pruning improve certified robustness of neural networks? [106.03070538582222]
  We show that neural network pruning can improve empirical robustness of deep neural networks (NNs) Our experiments show that by appropriately pruning an NN, its certified accuracy can be boosted up to 8.2% under standard training. We additionally observe the existence of certified lottery tickets that can match both standard and certified robust accuracies of the original dense models.
  arXiv  Detail & Related papers  (2022-06-15T05:48:51Z)

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.