SoK: Certified Robustness for Deep Neural Networks

preview_player
Показать описание
SoK: Certified Robustness for Deep Neural Networks
Linyi Li (University of Illinois Urbana-Champaign, USA), Tao Xie (Key Laboratory of High Confidence Software Technologies, MoE (Peking University), China), Bo Li (University of Illinois Urbana-Champaign, USA)
  1. IEEE Symposium on Security and Privacy
Рекомендации по теме
SoK: Certified Robustness 0:14:56

SoK: Certified Robustness for Deep Neural Networks

Certified Robustness to 0:00:38

Certified Robustness to Adversarial Examples with Differential Privacy

Towards Analyzing Semantic 0:05:01

Towards Analyzing Semantic Robustness of Deep Neural Networks (ECCVW 2020)

[CVPR 2023] Towards 0:07:35

[CVPR 2023] Towards Compositional Adversarial Robustness

Lecture 10-Deep Learning 1:12:37

Lecture 10-Deep Learning Foundations by Soheil Feizi:Provable & Generalizable Adversarial Robust...

Robust Deep Neural 0:05:02

Robust Deep Neural Networks | 5-Minute PhD Research Overview

Ruth Urner | 0:18:46

Ruth Urner | Robustness Should not be at Odds with Accuracy

Lecture 5 - 0:55:29

Lecture 5 - Differential Privacy for Adversarial Robustness

CVPR 2021 Towards 0:04:55

CVPR 2021 Towards Evaluating and Training Verifiably Robust Neural Networks

SaTML 2023 - 1:01:51

SaTML 2023 - Zico Kolter - Robustness in Machine Learning: A Five-Year Retrospective

Certified Robustness: Fundamentals 0:54:26

Certified Robustness: Fundamentals and Challenges. Aleksandr Petiushko, Nuro, USA

Neural Networks with 1:08:11

Neural Networks with Provable Robustness Guarantees

Reliable and Interpretable 1:04:16

Reliable and Interpretable Artificial Intelligence -- Lecture 12 (Randomized Smoothing)

SoK: General Purpose 0:01:01

SoK: General Purpose Compilers for Secure Multi-Party Computation

[L4DC 2022] A 0:00:53

[L4DC 2022] A Simple and Efficient Sampling-based Reachability Analysis Algorithm (Hardware Results)

USENIX Security '21 0:12:18

USENIX Security '21 - Dirty Road Can Attack: Security of Deep Learning based Automated Lane

High-frequency Component Helps 0:57:09

High-frequency Component Helps Explain the Generalization of Convolutional Neural Networks | AISC

Train but Verify: 0:18:58

Train but Verify: Towards Practical AI Robustness

DeepSec: A Uniform 0:01:01

DeepSec: A Uniform Platform for Security Analysis of Deep Learning Models

NEUZZ: Efficient Fuzzing 0:01:01

NEUZZ: Efficient Fuzzing with Neural Program Smoothing

SoK: Security Evaluation 0:01:06

SoK: Security Evaluation of Home-Based IoT Deployment

L. Grüne. Curse-of-dimensionality-free 0:49:25

L. Grüne. Curse-of-dimensionality-free Lyapunov functions via ISS small-gain & neural networks

Defense Against the 0:56:44

Defense Against the Dark Arts

NDSS 2019 - 0:16:21

NDSS 2019 - Adversarial Attacks Against ASR Systems via Psychoacoustic Hiding