arXiv research

Adversarial dynamics embedding improves MLE of exponential family models.

DAAN dynamically adapts adversarial learning for better domain adaptation.

New algorithm tackles dynamic query routing to multiple embedding models.

Adversarial training adds dynamic perturbations to neural networks for robustness.

DAWN dynamically embeds watermarks in neural network predictions to prevent model extraction.

AROS uses Lyapunov-stabilized embeddings to improve out-of-distribution detection robustness against adversarial attacks.

StealthRank subtly boosts LLM rankings without detectable anomalies.

Adversarial training improves network embedding models.

IDGL learns better graph structure and embeddings iteratively.

New method for black-box adversarial attacks using pretrained model embeddings.

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the laten…

Advances AT with HE to improve model robustness.

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding dis…

NewsNet-SDF uses deep learning to integrate financial news with financial data for better asset pricing.

Paper proposes a black-box adversarial attack method for graph embedding models.

APGE protects graph node representations from inference attacks.

Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively generated adversarial images easily transfer between networks trained with the same strategy. Inspir…

This paper improves continuous adversarial training for LLMs using in-context learning theory.

Adversarial ASV improves speaker verification robustness.

The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no study of their robustness to adversarial attacks. We provide the first adversari…

Adversarial training improves graph autoencoder generalization.

New method improves interpretability of text adversarial examples.

EI-MTD defends edge intelligence against adversarial attacks with dynamic scheduling.

Adversarial framework enforces fairness constraints on graph embeddings.

Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the image processing field to the input word embedding space instead of the discrete…

Dynamic defense against Byzantine poisoning in federated learning.

AVDA transfers knowledge from source to target domains using embeddings.

Improved neural language models using adversarial training.

In a graph convolutional network, we assume that the graph $G$ is generated wrt some observation noise. During learning, we make small random perturbations $ΔG$ of the graph and try to improve generalization. Based on quantum information geometry, $ΔG$ can be characterized by the eigendecomposition of the graph Laplaci…

Robust RL improves controller robustness to dynamics variations using adversarial populations.

Generative models for complex stochastic dynamics using adversarial learning.

Network embedding represents nodes in a continuous vector space and preserves structure information from the Network. Existing methods usually adopt a "one-size-fits-all" approach when concerning multi-scale structure information, such as first- and second-order proximity of nodes, ignoring the fact that different scal…

Quantized neural networks are vulnerable to adversarial attacks.

End-to-end speaker verification framework reduces text dependency.

Generative model solves financial market equilibria with stable reinforcement learning.

This paper debiases KG embeddings by filtering sensitive attributes.

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations to numerous entries of the input vector, which is inappropriat…

Improves adversarial robustness of DEQ models by regulating neural dynamics.

The paper tackles adversarial attacks on recurrent neural networks.

DADI framework dynamically discovers fair information using reinforcement learning.

DANE adapts network embeddings across multiple domains.

Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.

Study on adversarial training dynamics in high dimensions using SGD.

Network representation learning in low dimensional vector space has attracted considerable attention in both academic and industrial domains. Most real-world networks are dynamic with addition/deletion of nodes and edges. The existing graph embedding methods are designed for static networks and they cannot capture evol…

STRATA generates code adversarial examples efficiently without gradients.

LOGAN optimizes GAN training by improving adversarial dynamics.

ADEC addresses feature randomness and drift in autoencoder-based clustering.

Paper proposes a new method for predicting drug interactions using adversarial autoencoders.