No article text was recorded for this version.
robustness-accuracy trade-off (clean accuracy degradation)
Version 1 of 13,601 papers5,083 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Architecture Selection via the Trade-off Between Accuracy and Robustness
- Blog: Is Robustness the Cost of Accuracy? - A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
- Blog: Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
- Blog: Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off
- Blog: Theoretically Principled Trade-off between Robustness and Accuracy
- Blog: On the relationship between class selectivity, dimensionality, and robustness
- Blog: Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models
- Blog: Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms
- Blog: Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
- Blog: Sharpness-Aware Minimization Alone can Improve Adversarial Robustness
- Blog: On the uncertainty principle of neural networks
- Blog: Precise Tradeoffs in Adversarial Training for Linear Regression
- Blog: Data Quality Matters For Adversarial Training: An Empirical Study
- Blog: On the uncertainty principle of neural networks
- Blog: Is Robustness the Cost of Accuracy? - A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
- Blog: Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
- Blog: Adversarial Training and Robustness for Multiple Perturbations
- Blog: You Don’t Need Robust Machine Learning to Manage Adversarial Attack Risks
- Blog: When Should You Defend Your Classifier? - - A Game-Theoretical Analysis of Countermeasures Against Adversarial Examples
- Blog: A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification
- Blog: Fundamental Tradeoffs in Distributionally Adversarial Training
- Blog: Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness
- Blog: Adversarial Learning with Cost-Sensitive Classes
- Blog: Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity
- Blog: Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning
- Blog: Adversarial Fine-tune with Dynamically Regulated Adversary
- Blog: A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions
- Blog: Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks
- Blog: RAMP: Boosting Adversarial Robustness Against Multiple lp Perturbations for Universal Robustness
- Blog: Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning
- Blog: Delving into the Adversarial Robustness on Face Recognition
- Blog: Learning to Generate Noise for Robustness against Multiple Perturbations
- Blog: Adversarial Robustness of Flow-Based Generative Models
- Blog: Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff
- Blog: The Dimpled Manifold Model of Adversarial Examples in Machine Learning
- Blog: Towards Robust Vision Transformer
- Blog: Why adversarial training can hurt robust accuracy
- Blog: ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
- Blog: On the Limitations of Stochastic Pre-processing Defenses
- Blog: Conflict-Aware Adversarial Training
- Blog: Improving robustness of language models from a geometry-aware perspective
- Blog: A Critical Evaluation of Open-World Machine Learning
- Blog: Towards robust sensing for Autonomous Vehicles: An adversarial perspective
- Blog: A Frequency Perspective of Adversarial Robustness
- Blog: Stance Detection Benchmark: How Robust Is Your Stance Detection?
- Blog: Adversarial Robustness of Flow-Based Generative Models
- Blog: Defenses in Adversarial Machine Learning: A Survey
- Blog: Mitigating Accuracy-Robustness Trade-Off via Balanced Multi-Teacher Adversarial Distillation
- Blog: On the Trade-offs between Adversarial Robustness and Actionable Explanations
- Blog: Batch Normalization Increases Adversarial Vulnerability: Disentangling Usefulness and Robustness of Model Features
- Blog: When Should You Defend Your Classifier? - - A Game-Theoretical Analysis of Countermeasures Against Adversarial Examples
- Blog: Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
- Blog: CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval
- Blog: Does Robustness on ImageNet Transfer to Downstream Tasks?
- Blog: Precise statistical analysis of classification accuracies for adversarial training
- Blog: Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses
- Blog: Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness
- Blog: When Bots Take Over the Stock Market: Evasion Attacks Against Algorithmic Traders
- Blog: Targeted Adversarial Attacks on Wind Power Forecasts
- Blog: Provable Tradeoffs in Adversarially Robust Classification
Showing 60 of 3,601 papers.
History & citation
Current · Permanent link
- Fisher Information Regularization for Robust Neural Networks merged into this direction (54% overlap)
- Selective Activation of Adversarial Defense Mechanisms merged into this direction (56% overlap)
- Direct Optimization of Certified Safety Margins merged into this direction (53% overlap)
- The Fundamental Tradeoff Between Robustness and Performance merged into this direction (82% overlap)
- The Accuracy Robustness Trade-off in Deep Learning merged into this direction (94% overlap)
- The Robustness Accuracy Trade-off in Adversarial Learning merged into this direction (79% overlap)
- Reconciling Adversarial Robustness with Standard Classification Accuracy merged into this direction (100% overlap)
- Robustness Across Multiple Adversarial Perturbations merged into this direction (56% overlap)
- The Adversarial Robustness Ceiling merged into this direction (50% overlap)
- In-Situ Tunable Adversarial Robustness merged into this direction (87% overlap)
- The Limits of Scaling for Adversarial Robustness merged into this direction (54% overlap)
- Balancing Model Invariance and Semantic Sensitivity merged into this direction (61% overlap)
- Instance Adaptive Adversarial Training for Robust Neural Networks merged into this direction (61% overlap)
- Rejecting Adversarial Examples as Statistical Outliers merged into this direction (50% overlap)
- Bridging the Gap Between Robustness and Clean Accuracy merged into this direction (84% overlap)
- Smoothing Decision Surfaces with Defensive Distillation merged into this direction (67% overlap)
- Securing Graph Neural Networks Against Structural Perturbations merged into this direction (79% overlap)
- The Divergence of Adversarial and Natural Robustness merged into this direction (73% overlap)
- Multi-Layered Defense and Trade-offs in Machine Learning Security merged into this direction (50% overlap)
- Adversarial Purification with Generative Denoising merged into this direction (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_robustness_accuracy_trade_off_clean_accu_590c9060,
title = {robustness-accuracy trade-off (clean accuracy degradation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/robustness-accuracy-trade-off-clean-accuracy-degradation/rdr_590c9060732c41f78ac35e9f59246f29},
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_robustness_accuracy_trade_off_clean_accu_590c9060_v1,
title = {robustness-accuracy trade-off (clean accuracy degradation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/robustness-accuracy-trade-off-clean-accuracy-degradation/rdr_590c9060732c41f78ac35e9f59246f29/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}