Shades of Finality and Layer 2 Scaling
Comments 14 pages
作者
Dawn Song
AI / Security
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
Latent Execution for Neural Program Synthesis
Comments Published in NeurIPS 2021
Measuring Coding Challenge Competence With APPS
Comments NeurIPS 2021. Code and the APPS dataset is available at https://github.com/hendrycks/apps
Measuring Mathematical Problem Solving With the MATH Dataset
Comments NeurIPS 2021. Code and the MATH dataset is available at https://github.com/hendrycks/math/
Grounded Graph Decoding Improves Compositional Generalization in Question Answering
Comments To be published in Findings of EMNLP 2021. Code available at https://github.com/gaiyu0/cfq
Adversarial Examples for $k$-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams
Comments Appears at NeurIPS 2021. Code is available at https://github.com/wagner-group/geoadex
Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
Comments ICML 2021
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation
Comments EMNLP 2021; 14 pages, 5 figures, 9 tables
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
Comments ICCV 2021; Datasets, code, and models available at https://github.com/hendrycks/imagenet-r
DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Comments The 21st Privacy Enhancing Technologies Symposium (PETS), 2021
Extracting Training Data from Large Language Models
FED-$χ^2$: Privacy Preserving Federated Correlation Test
Towards Bidirectional Protection in Federated Learning
Practical One-Shot Federated Learning for Cross-Silo Setting
Chorus: a Programming Framework for Building Scalable Differential Privacy Mechanisms
Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
Proceedings of the AAAI-20 Workshop on Intelligent Process Automation (IPA-20)
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Model-Contrastive Federated Learning
Comments Accepted by CVPR 2021
REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data
Comments ACM Asia Conference on Computer and Communications Security (AsiaCCS), 2021. Early version in ICML 2019 Workshop on Security and Privacy of Machine Learning. The first two authors contribute equally
Advances and Open Problems in Federated Learning
Comments Published in Foundations and Trends in Machine Learning Vol 4 Issue 1. See: https://www.nowpublishers.com/article/Details/MAL-083
Natural Adversarial Examples
Comments CVPR 2021; dataset and code available at https://github.com/hendrycks/natural-adv-examples
A System for Automated Open-Source Threat Intelligence Gathering and Management
Comments Accepted paper at SIGMOD 2021 demonstrations track
A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence
Comments Accepted paper at ICDE 2021 demonstrations track. arXiv admin note: substantial text overlap with arXiv:2010.13637
Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
Comments Accepted paper at ICDE 2021
