paper-with-me

홈 › Papers

FANNet: Formal Analysis of Noise Tolerance, Training Bias and Input Sensitivity in Neural Networks

2019-12-03 · Mahum Naseer, Mishal Fatima Minhas, Faiq Khalid, Muhammad Abdullah Hanif, Osman Hasan, Muhammad Shafique

With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems. However, despite their impressive performance on "known inputs", these NNs can fail absurdly on the "unseen inputs", especially if these real-time inputs deviate from the training dataset distributions, or contain certain types of input noise. This indicates the low noise tolerance of NNs, which is a major reason for the recent increase of adversarial attacks. This is a serious concern, particularly for safety-critical applications, where inaccurate results lead to dire consequences. We propose a novel methodology that leverages model checking for the Formal Analysis of Neural Network (FANNet) under different input noise ranges. Our methodology allows us to rigorously analyze the noise tolerance of NNs, their input node sensitivity, and the effects of training bias on their performance, e.g., in terms of classification accuracy. For evaluation, we use a feed-forward fully-connected NN architecture trained for the Leukemia classification. Our experimental results show $\pm 11\%$ noise tolerance for the given trained network, identify the most sensitive input nodes, and confirm the biasness of the available training dataset.

📄 PDF Abstract BibTeX arXiv:1912.01978

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationSensitivity

Similar Papers 제목 키워드 기반

Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)

2023-06-29 · Mahum Naseer, Osman Hasan, Muhammad Shafique

Owing to their remarkable learning capabilities and performance in real-world applications, the use of machine learning systems based on Neural Networks (NNs) has been continuously increasing. However, various case studi…

Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate

2024-10-02 · Jie Shen

Understanding noise tolerance of machine learning algorithms is a central quest in learning theory. In this work, we study the problem of computationally efficient PAC learning of halfspaces in the presence of malicious …

Learning TheoryPAC learning

Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions

2026-07-03 · Xinyun Lu, Haoang Chi, Zhiheng Zhang arxiv

In selective deployment, practitioners act only on a model-chosen subset of individuals based on predicted conditional average treatment effects, but marginal conformal guarantees need not control reliability on that sel…

Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning

2019-06-18 · Tadashi Kozuno, Dongqi Han, Kenji Doya

In real-world applications of reinforcement learning (RL), noise from inherent stochasticity of environments is inevitable. However, current policy evaluation algorithms, which plays a key role in many RL algorithms, are…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Fault Tolerance of Neural Networks in Adversarial Settings

2019-10-30 · Vasisht Duddu, N. Rajesh Pillai, D. Vijay Rao, Valentina E. Balas

Artificial Intelligence systems require a through assessment of different pillars of trust, namely, fairness, interpretability, data and model privacy, reliability (safety) and robustness against against adversarial atta…

Adversarial RobustnessFairness