Search Results for author:
Found 9 papers, 5 papers with code
Fast Adversarial Training against Textual Adversarial Attacks
Based on the observation that the adversarial perturbations crafted by single-step and multi-step gradient ascent are similar, FAT uses single-step gradient ascent to craft adversarial examples in the embedding space to expedite the training process.
PIAT: Parameter Interpolation based Adversarial Training for Image Classification
Besides, we suggest to use the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the clean and adversarial examples.
Robust Textual Embedding against Word-level Adversarial Attacks
We attribute the vulnerability of natural language processing models to the fact that similar inputs are converted to dissimilar representations in the embedding space, leading to inconsistent outputs, and we propose a novel robust training method, termed Fast Triplet Metric Learning (FTML).
Regional Adversarial Training for Better Robust Generalization
Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks.
Equality Saturation for Tensor Graph Superoptimization
However, we observe that existing approaches for tensor graph superoptimization both in production and research frameworks apply substitutions in a sequential manner.
Neurosymbolic Transformers for Multi-Agent Communication
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication.
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks
Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification. For text classification, however, existing synonym substitution based adversarial attacks are effective but not efficient to be incorporated into practical text adversarial training.
Natural Language Adversarial Defense through Synonym Encoding
In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side.
Correctness Verification of Neural Networks
The presented framework also enables detecting illegal inputs -- inputs that are not contained in (or close to) the target input space as defined by the state space and observation process (the neural network is not designed to work on them), so that we can flag when we don't have guarantees.
