Search Results for author:
Found 16 papers, 5 papers with code
Understanding and Visualizing the District of Columbia Capital Bikeshare System Using Data Analysis for Balancing Purposes
We also define two indices based on stations' shortages and surpluses that reflect the degree of balancing aid a station needs.
SCDA: School Compatibility Decomposition Algorithm for Solving the Multi-School Bus Routing and Scheduling Problem
A novel decomposition algorithm is proposed to solve the integrated model.
School bus routing by maximizing trip compatibility
Through importing the generated trips of the routing problems into the bus scheduling (blocking) problem, it is shown that the proposed model uses up to 13% fewer buses than the common traditional routing models.
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the labeling of training data.
Are adversarial examples inevitable?
Using experiments, we explore the implications of theoretical guarantees for real-world problems and discuss how factors such as dimensionality and image complexity limit a classifier's robustness against adversarial examples.
Universal Adversarial Training
Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels.
Adversarial Training for Free!
Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks.
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data.
Adversarially robust transfer learning
By training classifiers on top of these feature extractors, we produce new models that inherit the robustness of their parent networks.
Adversarial attacks on Copyright Detection Systems
Our goal is to raise awareness of the threats posed by adversarial examples in this space, and to highlight the importance of hardening copyright detection systems to attacks.
Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?
Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization.
WITCHcraft: Efficient PGD attacks with random step size
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points.
Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates
To deflect adversarial attacks, a range of "certified" classifiers have been proposed.
Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training
Our adaptive networks also outperform larger widened non-adaptive architectures that have 1. 5 times more parameters.
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer
Further, we demonstrate that the compact structure and corresponding initialization from the Lottery Ticket Hypothesis can also help in data-free training.
Improving Robustness with Adaptive Weight Decay
We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration.
