Improved techniques for deterministic l2 robustness

von Singla, Sahil
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 21 of 50 (2023)

(DE)RANDOMIZED SMOOTHING FOR CERTIFIABLE DEFENSE AGAINST PATCH ATTACKS

von Levine, Alexander
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 8 of 27 (2021)

SKEW ORTHOGONAL CONVOLUTIONS

von SINGLA, SAHIL
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 13 of 16 (2022)

SECOND-ORDER PROVABLE DEFENSES AGAINST ADVERSARIAL ATTACKS

von Singla, Sahil
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 12 of 15 (2021)

FUNCTIONAL ADVERSARIAL ATTACKS

von Laidlaw, Cassidy
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 14 of 20 (2020)

FOCUS: Familiar Objects in Common and Uncommon Settings

von Kattakinda, Priyatham
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 13 of 33 (2023)

IMPROVED, DETERMINISTIC SMOOTHING FOR L_1 CERTIFIED ROBUSTNESS

von LEVINE, ALEXANDER
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 8 of 16 (2022)

Lethal Dose Conjecture on Data Poisoning

von Wang, Wenxiao
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 3 of 50 (2023)

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation

von Balaji, Yogesh
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 16 of 27 (2021)

Hard ImageNet: Segmentations for Objects with Strong Spurious Cues

von Moayeri, Mazda
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 14 of 50 (2023)

Toward Efficient Robust Training against Union of ℓp Threat Models

von Sriramanan, Gaurang
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 34 of 50 (2023)

ON SECOND-ORDER GROUP INFLUENCE FUNCTIONS FOR BLACK-BOX PREDICTIONS

von Basu, Samyadeep
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 1 of 15 (2021)

Explicit Tradeoffs between Adversarial and Natural Distributional Robustness

von Moayeri, Mazda
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 50 of 50 (2023)

Improved Certified Defenses Against Data Poisoning with (Deterministic) Finite Aggregation

von Wang, Wenxiao
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 28 of 33 (2023)

Improving Deep Learning Interpretability by Saliency Guided Training

von Ismail, Aya Abdelsalam
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 32 of 36 (2022)

CURSE OF DIMENSIONALITY ON RANDOMIZED SMOOTHING FOR CERTIFIABLE ROBUSTNESS

von Kumar, Aounon
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 7 of 15 (2021)

CERTIFYING CONFIDENCE VIA RANDOMIZED SMOOTHING

von Kumar, Aounon
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 7 of 27 (2021)

BENCHMARKING DEEP LEARNING INTERPRETABILITY IN TIME SERIES PREDICTIONS

von Ismail, Aya Abdelsalam
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 8 of 27 (2021)

QUANTUM WASSERSTEIN GENERATIVE ADVERSARIAL NETWORKS

von Chakrabarti, Shouvanik
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 9 of 20 (2020)

UNSUPERVISED ANOMALY DETECTION WITH ADVERSARIAL MIRRORED AUTOENCODERS

von Somepalli, Gowthami
Veröffentlicht in Conference on Uncertainty in Artificial Intelligence (37. : 2021 : Online) 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021) ; Part 1 of 3 (2022)