paper-with-me

홈 › Papers

GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations

2023-07-05 · Julia Lust, Alexandru P. Condurache

Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on adversarial attacks or out-of-distribution samples as reasons for false predictions. However, generalization errors occur due to diverse reasons often related to poorly learning relevant invariances. We therefore propose GIT, a holistic approach for the detection of generalization errors that combines the usage of gradient information and invariance transformations. The invariance transformations are designed to shift misclassified samples back into the generalization area of the neural network, while the gradient information measures the contradiction between the initial prediction and the corresponding inherent computations of the neural network using the transformed sample. Our experiments demonstrate the superior performance of GIT compared to the state-of-the-art on a variety of network architectures, problem setups and perturbation types.

📄 PDF Abstract BibTeX arXiv:2307.02672

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Gradients as a Measure of Uncertainty in Neural Networks

2020-08-18 · Jinsol Lee, Ghassan AlRegib

Despite tremendous success of modern neural networks, they are known to be overconfident even when the model encounters inputs with unfamiliar conditions. Detecting such inputs is vital to preventing models from making n…

Out-of-Distribution Detection

Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection

2019-09-25 · Nilesh A. Ahuja, Ibrahima Ndiour, Trushant Kalyanpur, Omesh Tickoo

We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametri…

Adversarial Attack

Gradient-Based Adversarial and Out-of-Distribution Detection

2022-06-16 · Jinsol Lee, Mohit Prabhushankar, Ghassan AlRegib

We propose to utilize gradients for detecting adversarial and out-of-distribution samples. We introduce confounding labels -- labels that differ from normal labels seen during training -- in gradient generation to probe …

Out-of-Distribution Detection

Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?

2020-10-28 · Anna-Kathrin Kopetzki, Bertrand Charpentier, Daniel Zügner, Sandhya Giri 외

Dirichlet-based uncertainty (DBU) models are a recent and promising class of uncertainty-aware models. DBU models predict the parameters of a Dirichlet distribution to provide fast, high-quality uncertainty estimates alo…

Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning

2019-01-08 · Andreas Sedlmeier, Thomas Gabor, Thomy Phan, Lenz Belzner 외

We consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the …

Bayesian InferenceDeep Reinforcement LearningOpen-Ended Question AnsweringOut-of-Distribution Detection+4