24 citations · 115 across the 57 of their papers we have counts for
24 papers · 1 filter
SoK: Rethinking Membership Inference in Tabular Machine Learning
Cristina Pêra, Tânia Carvalho, Maxime Cordy +1
Membership Inference Attacks (MIAs) are currently the dominant approach to evaluating privacy in machine learning applications. Despite their significance, several concerns remain…
Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs
Firas Bayram, Maxime Cordy
Adversarial detection on evolving attributed graphs faces two challenges: fraud labels arrive late or not at all, and natural distributional drift erodes any trained decision bound…
SoK: Challenges in Tabular Membership Inference Attacks
Cristina Pêra, Tânia Carvalho, Maxime Cordy +1
Membership Inference Attacks (MIAs) are currently a dominant approach for evaluating privacy in machine learning applications. Despite their significance in identifying records bel…
Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Review
Salijona Dyrmishi, Mohamed Djilani, Thibault Simonetto +2
Adversarial attacks in machine learning have been extensively reviewed in areas like computer vision and NLP, but research on tabular data remains scattered. This paper provides th…
Leveraging External Factors in Household-Level Electrical Consumption Forecasting using Hypernetworks
Fabien Bernier, Maxime Cordy, Yves Le Traon
Accurate electrical consumption forecasting is crucial for efficient energy management and resource allocation. While traditional time series forecasting relies on historical patte…
On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses
Mohamed Djilani, Thibault Simonetto, Karim Tit +4
Recent tabular Foundational Models (FM) such as TabPFN and TabICL, leverage in-context learning to achieve strong performance without gradient updates or fine-tuning. However, thei…
RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses
Mohamed Djilani, Salah Ghamizi, Maxime Cordy
Although adversarial robustness has been extensively studied in white-box settings, recent advances in black-box attacks (including transfer- and query-based approaches) are primar…
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
Thibault Simonetto, Salah Ghamizi, Maxime Cordy
While adversarial robustness in computer vision is a mature research field, fewer researchers have tackled the evasion attacks against tabular deep learning, and even fewer investi…
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
Thibault Simonetto, Salah Ghamizi, Maxime Cordy
State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings. However, the robustness of these models…
Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data
Thibault Simonetto, Salah Ghamizi, Antoine Desjardins +2
State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings. However, the robustness of these models…
Evaluating the Robustness of Test Selection Methods for Deep Neural Networks
Qiang Hu, Yuejun Guo, Xiaofei Xie +4
Testing deep learning-based systems is crucial but challenging due to the required time and labor for labeling collected raw data. To alleviate the labeling effort, multiple test s…
Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability
Martin Gubri, Maxime Cordy, Yves Le Traon
Transferability is the property of adversarial examples to be misclassified by other models than the surrogate model for which they were crafted. Previous research has shown that e…
On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing
Zeming Dong, Qiang Hu, Zhenya Zhang +5
Graph neural network (GNN)-based graph learning has been popular in natural language and programming language processing, particularly in text and source code classification. Typic…
LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity
Martin Gubri, Maxime Cordy, Mike Papadakis +2
We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surro…
Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment
Qiang Hu, Yuejun Guo, Maxime Cordy +4
Deep Neural Networks (DNNs) have gained considerable attention in the past decades due to their astounding performance in different applications, such as natural language modeling,…
LaF: Labeling-Free Model Selection for Automated Deep Neural Network Reusing
Qiang Hu, Yuejun Guo, Maxime Cordy +3
Applying deep learning to science is a new trend in recent years which leads DL engineering to become an important problem. Although training data preparation, model architecture d…
On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks
Salijona Dyrmishi, Salah Ghamizi, Thibault Simonetto +2
While the literature on security attacks and defense of Machine Learning (ML) systems mostly focuses on unrealistic adversarial examples, recent research has raised concern about t…
Robust Active Learning: Sample-Efficient Training of Robust Deep Learning Models
Yuejun Guo, Qiang Hu, Maxime Cordy +2
Active learning is an established technique to reduce the labeling cost to build high-quality machine learning models. A core component of active learning is the acquisition functi…
Adversarial Robustness in Multi-Task Learning: Promises and Illusions
Salah Ghamizi, Maxime Cordy, Mike Papadakis +1
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks. While most of the studies focus on single-task neural networks with computer vision datasets,…
MUTEN: Boosting Gradient-Based Adversarial Attacks via Mutant-Based Ensembles
Yuejun Guo, Qiang Hu, Maxime Cordy +2
Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which causes serious threats to security-critical applications. This motivated much research on providing mechan…
Influence-Driven Data Poisoning in Graph-Based Semi-Supervised Classifiers
Adriano Franci, Maxime Cordy, Martin Gubri +2
Graph-based Semi-Supervised Learning (GSSL) is a practical solution to learn from a limited amount of labelled data together with a vast amount of unlabelled data. However, due to…
Efficient and Transferable Adversarial Examples from Bayesian Neural Networks
Martin Gubri, Maxime Cordy, Mike Papadakis +2
An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity. We argue t…
Test Selection for Deep Learning Systems
Wei Ma, Mike Papadakis, Anestis Tsakmalis +2
Testing of deep learning models is challenging due to the excessive number and complexity of computations involved. As a result, test data selection is performed manually and in an…
Automated Search for Configurations of Deep Neural Network Architectures
Salah Ghamizi, Maxime Cordy, Mike Papadakis +1
Deep Neural Networks (DNNs) are intensively used to solve a wide variety of complex problems. Although powerful, such systems require manual configuration and tuning. To this end,…