No article text was recorded for this version.
latent-space adversarial training
Version 1 of 175 papers90 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models
- Blog: Reliably fast adversarial training via latent adversarial perturbation
- Blog: Towards Robust Neural Machine Translation
- Blog: Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
- Blog: Detecting Adversarial Examples on Deep Neural Networks With Mutual Information Neural Estimation
- Blog: Robust Pre-Training by Adversarial Contrastive Learning
- Blog: Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
- Blog: Probing the Robustness of Large Language Models Safety to Latent Perturbations
- Blog: Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders
- Blog: Boosting Adversarial Robustness Using Feature Level Stochastic Smoothing
- Blog: Defending Against Unforeseen Failure Modes with Latent Adversarial Training
- Blog: Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder
- Blog: Cascade Adversarial Machine Learning Regularized with a Unified Embedding
- Blog: Set Representation Auxiliary Learning with Adversarial Encoding Perturbation and Optimization
- Blog: Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
- Blog: Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts
- Blog: Joint Character-Level Word Embedding and Adversarial Stability Training to Defend Adversarial Text
- Blog: SemRoDe: Macro Adversarial Training to Learn Representations that are Robust to Word-Level Attacks
- Blog: Adversarial Training and Provable Defenses: Bridging the Gap
- Blog: Deep Adversarial Reinforcement Learning With Noise Compensation by Autoencoder
- Blog: RepMix: Representation Mixing for Robust Attribution of Synthesized Images
- Blog: Elastic Robust Unlearning of Specific Knowledge in Large Language Models
- Blog: Gaussian class-conditional simplex loss for accurate, adversarially robust deep classifier training
- Blog: Enhancing Adversarial Robustness for Deep Metric Learning
- Blog: Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
- Blog: Adversarial Neural Pruning with Latent Vulnerability Suppression
- Blog: Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation
- Blog: The Autoencoding Variational Autoencoder
- Blog: Adversarial attacks and adversarial robustness in computational pathology
- Blog: Alleviate Dataset Shift Problem in Fine-grained Entity Typing with Virtual Adversarial Training
- Blog: On Generalization of Graph Autoencoders with Adversarial Training
- Blog: Graph Adversarial Self-Supervised Learning
- Blog: CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
- Blog: Adversarial Feature Augmentation and Normalization for Visual Recognition
- Blog: DefenseFea: An Input Transformation Feature Searching Algorithm Based Latent Space for Adversarial Defense
- Blog: JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
- Blog: Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense
- Blog: Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
- Blog: Safe Self-Refinement for Transformer-based Domain Adaptation
- Blog: Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
- Blog: ARAE: Adversarially robust training of autoencoders improves novelty detection
- Blog: Closing the Train-Test Gap in World Models for Gradient-Based Planning
- Blog: Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
- Blog: PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
- Blog: Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
- Blog: The Amazing Stability of Flow Matching
- Blog: MSAP: Multi-Step Adversarial Perturbations on Recommender Systems Embeddings
- Blog: Regularized Conditional Alignment for Multi-Domain Text Classification
- Blog: Adversarially Robust Deep Multi-View Clustering: A Novel Attack and Defense Framework
- Blog: A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data and Overparameterization?
- Blog: Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains
- Blog: Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
- Blog: A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?
- Blog: CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models
- Blog: Context-based Virtual Adversarial Training for Text Classification with Noisy Labels
- Blog: Language-Driven Anchors for Zero-Shot Adversarial Robustness
- Blog: Latent Adversarial Training Improves the Representation of Refusal
- Blog: Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning (Student Abstract)
- Blog: Positive and Unlabeled Learning for Detecting Software Functional Clones with Adversarial Training
- Blog: Manifold Adversarial Augmentation for Neural Machine Translation
Showing 60 of 75 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_latent_space_adversarial_training_c4b09b3c,
title = {latent-space adversarial training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/latent-space-adversarial-training/rdr_c4b09b3c0f16416a84e128b0a3edc3de},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_latent_space_adversarial_training_c4b09b3c_v1,
title = {latent-space adversarial training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/latent-space-adversarial-training/rdr_c4b09b3c0f16416a84e128b0a3edc3de/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}