Search Results for author: Laure Berti-Equille

Found 11 papers, 5 papers with code

Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers

no code implementations30 Jan 2024 Lei Xu, Sarah Alnegheimish, Laure Berti-Equille, Alfredo Cuesta-Infante, Kalyan Veeramachaneni

Experimental results on 4 datasets and BERT and distilBERT classifiers show that SP-Defense improves \r{ho} by 14. 6% and 13. 9% and decreases the attack success rate of SP-Attack by 30. 4% and 21. 2% on two classifiers respectively, and decreases the attack success rate of existing attack methods that involve multiple-word perturbations.

Data Augmentation Sentence +2

Making the End-User a Priority in Benchmarking: OrionBench for Unsupervised Time Series Anomaly Detection

1 code implementation26 Oct 2023 Sarah Alnegheimish, Laure Berti-Equille, Kalyan Veeramachaneni

The framework provides universal abstractions to represent models, extensibility to add new pipelines and datasets, hyperparameter standardization, pipeline verification, and frequent releases with published benchmarks.

Anomaly Detection Benchmarking +2

Discovering Transition Pathways Towards Coviability with Machine Learning

no code implementations6 Jan 2023 Laure Berti-Equille, Rafael L. G. Raimundo

Coviability refers to the multiple socio-ecological arrangements and governance structures under which humans and nature can coexist in functional, fair, and persistent ways.

AER: Auto-Encoder with Regression for Time Series Anomaly Detection

3 code implementations27 Dec 2022 Lawrence Wong, Dongyu Liu, Laure Berti-Equille, Sarah Alnegheimish, Kalyan Veeramachaneni

We then propose AER (Auto-encoder with Regression), a joint model that combines a vanilla auto-encoder and an LSTM regressor to incorporate the successes and address the limitations of each method.

Anomaly Detection Benchmarking +3

Reconstruction of Long-Term Historical Demand Data

no code implementations10 Sep 2022 Reshmi Ghosh, Michael Craig, H. Scott Matthews, Constantine Samaras, Laure Berti-Equille

Long-term planning of a robust power system requires the understanding of changing demand patterns.

The Need for Interpretable Features: Motivation and Taxonomy

no code implementations23 Feb 2022 Alexandra Zytek, Ignacio Arnaldo, Dongyu Liu, Laure Berti-Equille, Kalyan Veeramachaneni

Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their features.

Decision Making

R&R: Metric-guided Adversarial Sentence Generation

1 code implementation17 Apr 2021 Lei Xu, Alfredo Cuesta-Infante, Laure Berti-Equille, Kalyan Veeramachaneni

It improves the quality of adversarial examples by optimizing a critique score which combines the fluency, similarity, and misclassification metrics.

Adversarial Attack General Classification +6

Are Outlier Detection Methods Resilient to Sampling?

no code implementations31 Jul 2019 Laure Berti-Equille, Ji Meng Loh, Saravanan Thirumuruganathan

In this paper, we introduce the notion of resilience to sampling for outlier detection methods.

Outlier Detection

Truth Discovery Algorithms: An Experimental Evaluation

1 code implementation23 Sep 2014 Dalia Attia Waguih, Laure Berti-Equille

A fundamental problem in data fusion is to determine the veracity of multi-source data in order to resolve conflicts.


Cannot find the paper you are looking for? You can Submit a new open access paper.