← Keywords

adversarial robustness

1335 papers

Explore in graph

Also known as

UAP PAR ADV AR

Co-occurring keywords

adversarial training (1261) adversarial attack (1599) neural network (6616) adversarial example (563) adversarial learning (1592) model robustness (478) adversarial defense (324) large language model (12755) certified robustness (116) adversarial perturbation (376)

Papers

Random Normalization Aggregation for Adversarial Defense NIPS 2022
Invariance-Aware Randomized Smoothing Certificates NIPS 2022
When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture NIPS 2022
Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach L4DC 2022
Phrase-level Textual Adversarial Attack with Label Preservation NAACL 2022
Adversarial Robustness of Deep Sensor Fusion Models WACV 2022
Efficient Robust Training via Backward Smoothing AAAI 2022
The King Is Naked: On the Notion of Robustness for Natural Language Processing AAAI 2022
KATG: Keyword-Bias-Aware Adversarial Text Generation for Text Classification AAAI 2022
Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection NIPS 2022
Gradient Methods Provably Converge to Non-Robust Networks NIPS 2022
Input-Specific Robustness Certification for Randomized Smoothing AAAI 2022
MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation AAAI 2022
Toward Efficient Robust Training against Union of $\ell_p$ Threat Models NIPS 2022
On Distributionally Robust Optimization and Data Rebalancing AISTATS 2022
Revisiting Sparse Convolutional Model for Visual Recognition NIPS 2022
Robust Probabilistic Time Series Forecasting AISTATS 2022
Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation NIPS 2022
On Global-view Based Defense via Adversarial Attack and Defense Risk Guaranteed Bounds AISTATS 2022
Variational Autoencoders: A Harmonic Perspective AISTATS 2022
Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness AISTATS 2022
Certifiably Robust Variational Autoencoders AISTATS 2022
Finding Dynamics Preserving Adversarial Winning Tickets AISTATS 2022
Diversified Adversarial Attacks based on Conjugate Gradient Method ICML 2022
Approximate Exploitability: Learning a Best Response IJCAI 2022