Search Results for author:
Found 9 papers, 3 papers with code
Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications
Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns for their application in safety-critical domains.
TrainSim: A Railway Simulation Framework for LiDAR and Camera Dataset Generation
The railway industry is searching for new ways to automate a number of complex train functions, such as object detection, track discrimination, and accurate train positioning, which require the artificial perception of the railway environment through different types of sensors, including cameras, LiDARs, wheel encoders, and inertial measurement units.
Robust-by-Design Classification via Unitary-Gradient Neural Networks
This work proposes a novel family of classifiers, namely Signed Distance Classifiers (SDCs), that, from a theoretical perspective, directly output the exact distance of x from the classification boundary, rather than a probability score (e. g., SoftMax).
CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models
Nevertheless, no much work has been devoted to the generation of datasets specifically designed to evaluate the adversarial robustness of neural models.
Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
This work presents Z-Mask, a robust and effective strategy to improve the adversarial robustness of convolutional networks against physically-realizable adversarial attacks.
On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
The existence of real-world adversarial examples (commonly in the form of patches) poses a serious threat for the use of deep learning models in safety-critical computer vision tasks such as visual perception in autonomous driving.
On the Minimal Adversarial Perturbation for Deep Neural Networks with Provable Estimation Error
In this regard, the Euclidean distance of the input from the classification boundary denotes a well-proved robustness assessment as the minimal affordable adversarial perturbation.
Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks
Finally, a printed physical billboard containing an adversarial patch was tested in an outdoor driving scenario to assess the feasibility of the studied attacks in the real world.
Increasing the Confidence of Deep Neural Networks by Coverage Analysis
The great performance of machine learning algorithms and deep neural networks in several perception and control tasks is pushing the industry to adopt such technologies in safety-critical applications, as autonomous robots and self-driving vehicles.
