MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs

• URL: http://arxiv.org/abs/2412.10186v2
• Date: Sun, 26 Oct 2025 11:06:59 GMT
• Title: MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
• Authors: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz,
• Abstract summary: Data errors, corruptions, and poisoning attacks during training pose a major threat to the reliability of modern AI systems.<n>We introduce MIBP-Cert, a novel certification method based on mixed-integer bilinear programming (MIBP)<n>By computing the set of parameters reachable through perturbed or manipulated data, we can predict all possible outcomes and guarantee robustness.
• Score: 50.41998220099097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data errors, corruptions, and poisoning attacks during training pose a major threat to the reliability of modern AI systems. While extensive effort has gone into empirical mitigations, the evolving nature of attacks and the complexity of data require a more principled, provable approach to robustly learn on such data - and to understand how perturbations influence the final model. Hence, we introduce MIBP-Cert, a novel certification method based on mixed-integer bilinear programming (MIBP) that computes sound, deterministic bounds to provide provable robustness even under complex threat models. By computing the set of parameters reachable through perturbed or manipulated data, we can predict all possible outcomes and guarantee robustness. To make solving this optimization problem tractable, we propose a novel relaxation scheme that bounds each training step without sacrificing soundness. We demonstrate the applicability of our approach to continuous and discrete data, as well as different threat models - including complex ones that were previously out of reach.

Related papers

• Data-driven stochastic reduced-order modeling of parametrized dynamical systems [3.5684665108045377]
  We introduce a data-driven framework for learning continuous-time ROMs that generalize across parameter spaces and forcing conditions.<n>We demonstrate excellent generalization to unseen parameter combinations and forcings, and significant efficiency gains compared to existing approaches.
  arXiv  Detail & Related papers  (2026-01-15T18:50:18Z)
• One Sample is Enough to Make Conformal Prediction Robust [53.78604391939934]
  We show that conformal prediction attains some robustness even with a forward pass on a single randomly perturbed input.<n>Our approach returns robust sets with smaller average set size compared to SOTA methods which use many (e.g. around 100) passes per input.
  arXiv  Detail & Related papers  (2025-06-19T19:14:25Z)
• AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing [64.79967583649407]
  Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences.<n>Existing KT models typically follow a single-step training paradigm, which leads to significant error accumulation.<n>We propose a novel Adversarial Multi-Step Training Framework for Knowledge Tracing (AdvKT) which focuses on the multi-step KT task.
  arXiv  Detail & Related papers  (2025-04-07T03:31:57Z)
• Disentangling Uncertainties by Learning Compressed Data Representation [2.959687944707463]
  We propose a framework that learns a neural network encoding of the data distribution and enables direct sampling from the output distribution.<n>Our approach incorporates a novel inference procedure based on Langevin dynamics sampling, allowing CDRM to predict arbitrary output distributions.
  arXiv  Detail & Related papers  (2025-03-20T02:37:48Z)
• Distilling Calibration via Conformalized Credal Inference [36.01369881486141]
  One way to enhance reliability is through uncertainty quantification via Bayesian inference. This paper introduces a low-complexity methodology to address this challenge by distilling calibration information from a more complex model. Experiments on visual and language tasks demonstrate that the proposed approach, termed Conformalized Distillation for Credal Inference (CD-CI), significantly improves calibration performance.
  arXiv  Detail & Related papers  (2025-01-10T15:57:23Z)
• Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing [12.513566361816684]
  Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Existing certified defenses for DEQs employing deterministic certification methods can not certify on large-scale datasets. We provide the first randomized smoothing certified defense for DEQs to solve these limitations.
  arXiv  Detail & Related papers  (2024-11-01T06:14:11Z)
• On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning [85.75164588939185]
  We study the discriminative probabilistic modeling on a continuous domain for the data prediction task of (multimodal) self-supervised representation learning.<n>We conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning.<n>We propose a novel non-parametric method for approximating the sum of conditional probability densities required by MIS.
  arXiv  Detail & Related papers  (2024-10-11T18:02:46Z)
• FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks [62.897993591443594]
  FullCert is the first end-to-end certifier with sound, deterministic bounds. We experimentally demonstrate FullCert's feasibility on two datasets.
  arXiv  Detail & Related papers  (2024-06-17T13:23:52Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Integer Programming for Learning Directed Acyclic Graphs from Non-identifiable Gaussian Models [6.54203362045253]
  We study the problem of learning directed acyclic graphs from continuous observational data.<n>We develop a mixed-integer programming framework for learning medium-sized problems.<n>Our method outperforms state-of-the-art algorithms and is robust to noise heteroscedasticity.
  arXiv  Detail & Related papers  (2024-04-19T02:42:13Z)
• MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection [76.97324120775475]
  Cross-domain keypoint detection methods always require accessing the source data during adaptation. This paper considers source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain.
  arXiv  Detail & Related papers  (2023-02-09T12:06:08Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond [57.10914865054868]
  We consider vertical logistic regression (VLR) trained with mini-batch descent gradient. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks.
  arXiv  Detail & Related papers  (2022-07-19T05:47:30Z)
• Online Learning Based Risk-Averse Stochastic MPC of Constrained Linear Uncertain Systems [0.0]
  This paper investigates the problem of designing data-driven Model Predictive Control (MPC) for linear time-invariant systems under additive disturbance. We propose a novel online learning based risk-varying MPC framework in which Conditional Value-at-Risk (CVaR) constraints are required to hold for a family of distributions called an ambiguity set.
  arXiv  Detail & Related papers  (2020-11-20T13:00:28Z)
• Sparse PCA: Algorithms, Adversarial Perturbations and Certificates [9.348107805982604]
  We study efficient algorithms for Sparse PCA in standard statistical models. Our goal is to achieve optimal recovery guarantees while being resilient to small perturbations.
  arXiv  Detail & Related papers  (2020-11-12T18:58:51Z)
• Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data [66.78671826743884]
  The distributionally robust optimization framework is considered for training a parametric model. The objective is to endow the trained model with robustness against adversarially manipulated input data. Proposed algorithms offer robustness with little overhead.
  arXiv  Detail & Related papers  (2020-07-07T18:25:25Z)
• Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable Robustness [15.38718018477333]
  We derive a new regularized risk, in which the regularizer can adaptively encourage the accuracy and robustness of the smoothed counterpart. We also design a new certification algorithm, which can leverage the regularization effect to provide tighter robustness lower bound that holds with high probability.
  arXiv  Detail & Related papers  (2020-02-17T20:54:34Z)
• Certified Robustness to Label-Flipping Attacks via Randomized Smoothing [105.91827623768724]
  Machine learning algorithms are susceptible to data poisoning attacks. We present a unifying view of randomized smoothing over arbitrary functions. We propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks.
  arXiv  Detail & Related papers  (2020-02-07T21:28:30Z)

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.