No article text was recorded for this version.
feature space crowding (semantic attack bias)
Version 1 of 173 papers116 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images
- Blog: Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
- Blog: The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images
- Blog: Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting
- Blog: Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy
- Blog: Towards Interpreting and Utilizing Symmetry Property in Adversarial Examples
- Blog: Not All Samples Are Equal: Quantifying Instance-level Difficulty in Targeted Data Poisoning
- Blog: Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy
- Blog: Semantically Adversarial Learnable Filters
- Blog: Analysis and Applications of Class-wise Robustness in Adversarial Training
- Blog: Semantic Subgraph Extraction Attacks To Convolutional Neural Networks
- Blog: A Hierarchical Assessment of Adversarial Severity
- Blog: Maintaining Perceptual Faithfulness of Adversarial Image Examples by Leveraging Color Variance
- Blog: Analysis and Applications of Class-wise Robustness in Adversarial Training
- Blog: MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning
- Blog: Fooling Contrastive Language-Image Pre-Trained Models with CLIPMasterPrints
- Blog: TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability
- Blog: DeHiB: Deep Hidden Backdoor Attack on Semi-supervised Learning via Adversarial Perturbation
- Blog: Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes
- Blog: Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features
- Blog: Random Untargeted Adversarial Example on Deep Neural Network
- Blog: Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis
- Blog: Data-Efficient Backdoor Attacks
- Blog: Kalt: generating adversarial explainable chinese legal texts
- Blog: NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion
- Blog: Adversarial Fooling Beyond "Flipping the Label"
- Blog: What Really is a Member? Discrediting Membership Inference via Poisoning
- Blog: Learning Ordered Top-k Adversarial Attacks via Adversarial Distillation
- Blog: Detecting Backdoor Attacks Against Point Cloud Classifiers
- Blog: Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints
- Blog: Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
- Blog: Training with Honeypots: Reshaping How LLMs Fail Under Adversarial Attacks
- Blog: Patch Attack Invariance: How Sensitive are Patch Attacks to 3D Pose?
- Blog: Adversarial Item Promotion on Visually-Aware Recommender Systems by Guided Diffusion
- Blog: Analysis of dominant classes in universal adversarial perturbations
- Blog: Towards the Memorization Effect of Neural Networks in Adversarial Training
- Blog: Revealing vulnerable regions through diverse adversarial examples
- Blog: One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models
- Blog: IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness
- Blog: Clustering Effect of (Linearized) Adversarial Robust Models
- Blog: Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
- Blog: Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors
- Blog: A Deep Dive into Adversarial Robustness in Zero-Shot Learning
- Blog: Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners
- Blog: On the reversibility of adversarial attacks
- Blog: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLMs Jailbreakers
- Blog: Scratch that! An Evolution-based Adversarial Attack against Neural Networks
- Blog: FDA: Feature Disruptive Attack
- Blog: Revisiting Adversarial Training Under Long-Tailed Distributions
- Blog: On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
- Blog: Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
- Blog: Goal-guided Generative Prompt Injection Attack on Large Language Models
- Blog: DAFA: Distance-Aware Fair Adversarial Training
- Blog: Semantic Representation Attack against Aligned Large Language Models
- Blog: Synthesizing Robust Adversarial Examples
- Blog: One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models
- Blog: Exploring misclassifications of robust neural networks to enhance adversarial attacks
- Blog: Generating Distributional Adversarial Examples to Evade Statistical Detectors
- Blog: Minimum Power Adversarial Attacks in Communication Signal Modulation Classification with Deep Learning
- Blog: On the Robustness of Face Recognition Algorithms Against Attacks and Bias
Showing 60 of 73 papers.
History & citation
Current · Permanent link
- Semantic Misclassification and Adversarial Severity merged into this direction (75% overlap)
- Adversarial Vulnerability in Semantic Class Hierarchies merged into this direction (55% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_feature_space_crowding_semantic_attack_b_ea0bad4a,
title = {feature space crowding (semantic attack bias)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/feature-space-crowding-semantic-attack-bias/rdr_ea0bad4abc94469aa62341d7543b0c21},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_feature_space_crowding_semantic_attack_b_ea0bad4a_v1,
title = {feature space crowding (semantic attack bias)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/feature-space-crowding-semantic-attack-bias/rdr_ea0bad4abc94469aa62341d7543b0c21/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}