Search Results for author:
Found 16 papers, 8 papers with code
RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses
Although adversarial robustness has been extensively studied in white-box settings, recent advances in black-box attacks (including transfer- and query-based approaches) are primarily benchmarked against weak defenses, leaving a significant gap in the evaluation of their effectiveness against more recent and moderate robust models (e. g., those featured in the Robustbench leaderboard).
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
In addition to our open benchmark (https://github. com/serval-uni-lu/tabularbench) where we welcome submissions of new models and defenses, we implement 7 robustification mechanisms inspired by state-of-the-art defenses in computer vision and propose the largest benchmark of robust tabular deep learning over 200 models across five critical scenarios in finance, healthcare and security.
SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Grids
We provide at https://github. com/yamizi/SafePowerGraph our open-source repository, a comprehensive leaderboard, a dataset and model zoo and expect our framework to standardize and advance research in the critical field of GNN for power systems.
Robustness Analysis of AI Models in Critical Energy Systems
This paper analyzes the robustness of state-of-the-art AI-based models for power grid operations under the $N-1$ security criterion.
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings.
PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-Phase Distribution Systems
PowerFlowMultiNet outperforms traditional methods and other deep learning approaches in terms of accuracy and computational speed.
Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data
State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings.
Hazards in Deep Learning Testing: Prevalence, Impact and Recommendations
To this end, we survey the related literature and identify 10 commonly adopted empirical evaluation hazards that may significantly impact experimental results.
How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks
Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions.
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models.
On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural Networks.
On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks
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 the under-explored field of realistic adversarial attacks and their implications on the robustness of real-world systems.
A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space
We propose a unified framework to generate feasible adversarial examples that satisfy given domain constraints.
Adversarial Robustness in Multi-Task Learning: Promises and Illusions
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks.
Adversarial Embedding: A robust and elusive Steganography and Watermarking technique
The key idea of our method is to use deep neural networks for image classification and adversarial attacks to embed secret information within images.
Automated Search for Configurations of Deep Neural Network Architectures
First, we model the variability of DNN architectures with a Feature Model (FM) that generalizes over existing architectures.
