v1v2v3v4v5v6v7v8v9 (latest)

SoK: Certified Robustness for Deep Neural Networks

IEEE Symposium on Security and Privacy (IEEE S&P), 2020

9 September 2020

Papers citing "SoK: Certified Robustness for Deep Neural Networks"

37 / 87 papers shown

MDTD: A Multi Domain Trojan Detector for Deep Neural NetworksConference on Computer and Communications Security (CCS), 2023

Bhaskar Ramasubramanian

J. Ritcey

Radha Poovendran

AAML

194

30 Aug 2023

DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local SmoothingUSENIX Security Symposium (USENIX Security), 2023

218

28 Aug 2023

General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized SmoothingEuropean Conference on Artificial Intelligence (ECAI), 2023

218

17 Aug 2023

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial AttacksIEEE Symposium on Security and Privacy (IEEE S&P), 2023

366

31 Jul 2023

Universal and Transferable Adversarial Attacks on Aligned Language Models

J. Zico Kolter

623

2,269

27 Jul 2023

Visual Adversarial Examples Jailbreak Aligned Large Language ModelsAAAI Conference on Artificial Intelligence (AAAI), 2023

Kaixuan Huang

Mengdi Wang

284

267

22 Jun 2023

Wasserstein distributional robustness of neural networksNeural Information Processing Systems (NeurIPS), 2023

289

16 Jun 2023

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness

251

14 Jun 2023

Precise and Generalized Robustness Certification for Neural NetworksUSENIX Security Symposium (USENIX Security), 2023

179

11 Jun 2023

DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound PropagationAAAI Conference on Artificial Intelligence (AAAI), 2023

Haitham Khedr

Yasser Shoukry

189

22 May 2023

Raising the Bar for Certified Adversarial Robustness with Diffusion Models

214

17 May 2023

When Deep Learning Meets Polyhedral Theory: A Survey

661

29 Apr 2023

Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time AttackerNeural Information Processing Systems (NeurIPS), 2023

237

21 Feb 2023

A Review of the Role of Causality in Developing Trustworthy AI Systems

...

321

14 Feb 2023

Reliability Assurance for Deep Neural Network Architectures Against Numerical DefectsInternational Conference on Software Engineering (ICSE), 2023

290

13 Feb 2023

A Rigorous Uncertainty-Aware Quantification Framework Is Essential for Reproducible and Replicable Machine Learning WorkflowsDigital Discovery (DD), 2023

289

13 Jan 2023

Confidence-aware Training of Smoothed Classifiers for Certified RobustnessAAAI Conference on Artificial Intelligence (AAAI), 2022

391

18 Dec 2022

Accelerating Certified Robustness Training via Knowledge TransferNeural Information Processing Systems (NeurIPS), 2022

Pratik Vaishnavi

Kevin Eykholt

Amir Rahmati

196

25 Oct 2022

$LOT: Layer-wise Orthogonal Training on Improving $\ell_2$ Certified Robustness$

LOT: Layer-wise Orthogonal Training on Improving

\ell_2

Certified RobustnessNeural Information Processing Systems (NeurIPS), 2022

220

20 Oct 2022

Robustness Certification of Visual Perception Models via Camera Motion SmoothingConference on Robot Learning (CoRL), 2022

Ding Zhao

188

04 Oct 2022

CARE: Certifiably Robust Learning with Reasoning via Variational Inference

381

12 Sep 2022

GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram PredictionMachine Learning in Health Care (MLHC), 2022

Ding Zhao

175

02 Aug 2022

Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification PerspectiveIEEE Transactions on Dependable and Secure Computing (TDSC), 2022

Mark Huasong Meng

197

24 Jun 2022

MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic

295

13 May 2022

Ensuring DNN Solution Feasibility for Optimization Problems with Convex Constraints and Its Application to DC Optimal Power Flow Problems

311

15 Dec 2021

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

Sejun Park

186

17 Nov 2021

Certifiers Make Neural Networks Vulnerable to Availability Attacks

Tobias Lorenz

Marta Kwiatkowska

Mario Fritz

AAML SILM

297

25 Aug 2021

On the Certified Robustness for Ensemble Models and BeyondInternational Conference on Learning Representations (ICLR), 2021

287

22 Jul 2021

Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks

Yulong Cao*

Ningfei Wang*

Qi Alfred Chen

223

278

17 Jun 2021

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time AdversariesInternational Conference on Machine Learning (ICML), 2021

206

16 Apr 2021

Improved, Deterministic Smoothing for L_1 Certified RobustnessInternational Conference on Machine Learning (ICML), 2021

Alexander Levine

Soheil Feizi

AAML

248

17 Mar 2021

Certified Robustness to Programmable Transformations in LSTMsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021

167

15 Feb 2021

Machine Learning (In) Security: A Stream of Problems

Luiz Eduardo Soares de Oliveira

Heitor Murilo Gomes

André Grégio

AAML

295

30 Oct 2020

RAB: Provable Robustness Against Backdoor AttacksIEEE Symposium on Security and Privacy (IEEE S&P), 2020

584

183

19 Mar 2020

Improving Certified Robustness via Statistical Learning with Logical ReasoningNeural Information Processing Systems (NeurIPS), 2020

...

629

28 Feb 2020

TSS: Transformation-Specific Smoothing for Robustness CertificationConference on Computer and Communications Security (CCS), 2020

436

27 Feb 2020

Principled Deep Neural Network Training through Linear Programming

D. Bienstock

Gonzalo Muñoz

Sebastian Pokutta

239

07 Oct 2018