Learning atomic forces from uncertainty-calibrated adversarial attacks

• URL: http://arxiv.org/abs/2502.18314v2
• Date: Wed, 26 Feb 2025 09:28:13 GMT
• Title: Learning atomic forces from uncertainty-calibrated adversarial attacks
• Authors: Henrique Musseli Cezar, Tilmann Bodenstein, Henrik Andersen Sveinsson, Morten Ledum, Simen Reine, Sigbjørn Løland Bore,
• Abstract summary: We propose the Calibrated Adversarial Geometry Optimization (CAGO) algorithm to discover adversarial structures with user-assigned errors.<n>By performing geometry optimization for uncertainty, we reach adversarial structures with the user-assigned target MLIP prediction error.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adversarial approaches, which intentionally challenge machine learning models by generating difficult examples, are increasingly being adopted to improve machine learning interatomic potentials (MLIPs). While already providing great practical value, little is known about the actual prediction errors of MLIPs on adversarial structures and whether these errors can be controlled. We propose the Calibrated Adversarial Geometry Optimization (CAGO) algorithm to discover adversarial structures with user-assigned errors. Through uncertainty calibration, the estimated uncertainty of MLIPs is unified with real errors. By performing geometry optimization for calibrated uncertainty, we reach adversarial structures with the user-assigned target MLIP prediction error. Integrating with active learning pipelines, we benchmark CAGO, demonstrating stable MLIPs that systematically converge structural, dynamical, and thermodynamical properties for liquid water and water adsorption in a metal-organic framework within only hundreds of training structures, where previously many thousands were typically required.

Related papers

• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment. We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials [0.0]
  Twisted layered van-der-Waals materials often exhibit unique electronic and optical properties absent in their non-twisted counterparts. Here, we introduce a split machine-learned interatomic potential and dataset curation approach that separates intralayer and interlayer interactions. Our approach integrates seamlessly with various intralayer and interlayer interaction models, enabling computationally tractable relaxation of moir'e materials.
  arXiv  Detail & Related papers  (2025-03-19T17:14:02Z)
• MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception [0.35998666903987897]
  evasion attacks manipulate models by introducing precise perturbations to input data, causing erroneous predictions. Our approach begins with SHAP-based analysis to understand model vulnerabilities, crucial for devising targeted evasion strategies. The Optimal Epsilon technique, employing a Binary Search algorithm, efficiently determines the minimum epsilon needed for successful evasion.
  arXiv  Detail & Related papers  (2024-04-24T05:22:38Z)
• What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization [111.55277952086155]
  We study In-Context Learning (ICL) by addressing several open questions. We show that, without updating the neural network parameters, ICL implicitly implements the Bayesian model averaging algorithm. We prove that the error of pretrained model is bounded by a sum of an approximation error and a generalization error.
  arXiv  Detail & Related papers  (2023-05-30T21:23:47Z)
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction [55.77136037458667]
  We propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. We simultaneously improve accuracy and uncertainty calibration across challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-20T07:29:23Z)
• Lightweight, Uncertainty-Aware Conformalized Visual Odometry [2.429910016019183]
  Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics. Emerging edge robotics devices like insect-scale drones and surgical robots lack a computationally efficient framework to estimate VO's predictive uncertainties. This paper presents a novel, lightweight, and statistically robust framework that leverages conformal inference (CI) to extract VO's uncertainty bands.
  arXiv  Detail & Related papers  (2023-03-03T20:37:55Z)
• Fast and Accurate Error Simulation for CNNs against Soft Errors [64.54260986994163]
  We present a framework for the reliability analysis of Conal Neural Networks (CNNs) via an error simulation engine. These error models are defined based on the corruption patterns of the output of the CNN operators induced by faults. We show that our methodology achieves about 99% accuracy of the fault effects w.r.t. SASSIFI, and a speedup ranging from 44x up to 63x w.r.t.FI, that only implements a limited set of error models.
  arXiv  Detail & Related papers  (2022-06-04T19:45:02Z)
• Improving robustness of jet tagging algorithms with adversarial training [56.79800815519762]
  We investigate the vulnerability of flavor tagging algorithms via application of adversarial attacks. We present an adversarial training strategy that mitigates the impact of such simulated attacks.
  arXiv  Detail & Related papers  (2022-03-25T19:57:19Z)
• Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors [8.029049649310213]
  We introduce novel gradient-based uncertainty metrics and investigate them for different object detection architectures. Experiments show significant improvements in true positive / false positive discrimination and prediction of intersection over union. We also find improvement over Monte-Carlo dropout uncertainty metrics and further significant boosts by aggregating different sources of uncertainty metrics.
  arXiv  Detail & Related papers  (2021-07-09T16:04:11Z)
• Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design [76.29738151117583]
  Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. We model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk.
  arXiv  Detail & Related papers  (2021-05-10T08:02:27Z)
• Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
  We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
  arXiv  Detail & Related papers  (2020-12-03T10:17:30Z)
• Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models [33.935755695805724]
  Learn-by-Calibrating (LbC) is a novel deep learning approach for designing emulators in scientific applications. We show that LbC provides significant improvements in generalization error over widely-adopted loss function choices. LbC achieves high-quality emulators even in small data regimes and more importantly, recovers the inherent noise structure without any explicit priors.
  arXiv  Detail & Related papers  (2020-05-05T16:54:11Z)

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.