paper-with-me

Papers

Deep Mining: Detecting Anomalous Patterns in Neural Network Activations with Subset Scanning

2020-01-01 · ICLR 2020 1 · Skyler Speakman, Celia Cintas, Victor Akinwande, Srihari Sridharan, Edward McFowland III

This work views neural networks as data generating systems and applies anomalous pattern detection techniques on that data in order to detect when a network is processing a group of anomalous inputs. Detecting anomalies is a critical component for multiple machine learning problems including detecting the presence of adversarial noise added to inputs. More broadly, this work is a step towards giving neural networks the ability to detect groups of out-of-distribution samples. This work introduces `Subset Scanning methods from the anomalous pattern detection domain to the task of detecting anomalous inputs to neural networks. Subset Scanning allows us to answer the question: "Which subset of inputs have larger-than-expected activations at which subset of nodes?" Framing the adversarial detection problem this way allows us to identify systematic patterns in the activation space that span multiple adversarially noised images. Such images are `"weird together". Leveraging this common anomalous pattern, we show increased detection power as the proportion of noised images increases in a test set. Detection power and accuracy results are provided for targeted adversarial noise added to CIFAR-10 images on a 20-layer ResNet using the Basic Iterative Method attack.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음
Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Subset Scanning Over Neural Network Activations

2018-10-19 · Skyler Speakman, Srihari Sridharan, Sekou Remy, Komminist Weldemariam 외

This work views neural networks as data generating systems and applies anomalous pattern detection techniques on that data in order to detect when a network is processing an anomalous input. Detecting anomalies is a crit…

ATD: Anomalous Topic Discovery in High Dimensional Discrete Data

2015-12-20 · Hossein Soleimani, David J. Miller

We propose an algorithm for detecting patterns exhibited by anomalous clusters in high dimensional discrete data. Unlike most anomaly detection (AD) methods, which detect individual anomalies, our proposed method detects…

Anomaly DetectionTopic ModelsVocal Bursts Intensity Prediction

Weakly Supervised Detection of Hallucinations in LLM Activations

2023-12-05 · Miriam Rateike, Celia Cintas, John Wamburu, Tanya Akumu 외

We propose an auditing method to identify whether a large language model (LLM) encodes patterns such as hallucinations in its internal states, which may propagate to downstream tasks. We introduce a weakly supervised aud…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model

Towards Creativity Characterization of Generative Models via Group-based Subset Scanning

2022-03-01 · Celia Cintas, Payel Das, Brian Quanz, Girmaw Abebe Tadesse 외

Deep generative models, such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), have been employed widely in computational creativity research. However, such models discourage out-of-distribut…

Towards creativity characterization of generative models via group-based subset scanning

2021-04-01 · Celia Cintas, Payel Das, Brian Quanz, Skyler Speakman 외

Deep generative models, such as Variational Autoencoders (VAEs), have been employed widely in computational creativity research. However, such models discourage out-of-distribution generation to avoid spurious sample gen…