Dawn Song

is this you? claim profile

∙ 0 followers
berkeley college

Professor of Computer Science Division at University of California, Berkeley

A System for Automated Open-Source Threat Intelligence Gathering and Management

Sophisticated cyber attacks have plagued many high-profile businesses. T...
01/19/2021 ∙ by Peng Gao, et al. ∙ 0 ∙ share

read it
A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence

Log-based cyber threat hunting has emerged as an important solution to c...
01/17/2021 ∙ by Peng Gao, et al. ∙ 0 ∙ share

read it
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

As machine learning systems grow in scale, so do their training data req...
12/18/2020 ∙ by Micah Goldblum, et al. ∙ 71 ∙ share

read it
Extracting Training Data from Large Language Models

It has become common to publish large (billion parameter) language model...
12/14/2020 ∙ by Nicholas Carlini, et al. ∙ 0 ∙ share

read it
PrivFramework: A System for Configurable and Automated Privacy Policy Compliance

Today's massive scale of data collection coupled with recent surges of c...
12/09/2020 ∙ by Usmann Khan, et al. ∙ 0 ∙ share

read it
Towards Defending Multiple Adversarial Perturbations via Gated Batch Normalization

There is now extensive evidence demonstrating that deep neural networks ...
12/03/2020 ∙ by Aishan Liu, et al. ∙ 0 ∙ share

read it
Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams

Adversarial examples are a widely studied phenomenon in machine learning...
11/19/2020 ∙ by Chawin Sitawarin, et al. ∙ 24 ∙ share

read it
Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence

Log-based cyber threat hunting has emerged as an important solution to c...
10/26/2020 ∙ by Peng Gao, et al. ∙ 15 ∙ share

read it
Language Models are Open Knowledge Graphs

This paper shows how to construct knowledge graphs (KGs) from pre-traine...
10/22/2020 ∙ by Chenguang Wang, et al. ∙ 0 ∙ share

read it
F2ED-Learning: Good Fences Make Good Neighbors

In this paper, we present F2ED-Learning, the first federated learning pr...
10/02/2020 ∙ by Lun Wang, et al. ∙ 1 ∙ share

read it
Model-Agnostic Round-Optimal Federated Learning via Knowledge Transfer

Federated learning enables multiple parties to collaboratively learn a m...
10/02/2020 ∙ by Qinbin Li, et al. ∙ 1 ∙ share

read it
A Principled Approach to Data Valuation for Federated Learning

Federated learning (FL) is a popular technique to train machine learning...
09/14/2020 ∙ by Tianhao Wang, et al. ∙ 25 ∙ share

read it
Measuring Massive Multitask Language Understanding

We propose a new test to measure a text model's multitask accuracy. The ...
09/07/2020 ∙ by Dan Hendrycks, et al. ∙ 28 ∙ share

read it
Compositional Generalization via Neural-Symbolic Stack Machines

Despite achieving tremendous success, existing deep learning models have...
08/15/2020 ∙ by Xinyun Chen, et al. ∙ 6 ∙ share

read it
Aligning AI With Shared Human Values

We show how to assess a language model's knowledge of basic concepts of ...
08/05/2020 ∙ by Dan Hendrycks, et al. ∙ 13 ∙ share

read it
Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis

The use of deep learning techniques has achieved significant progress fo...
07/16/2020 ∙ by Kavi Gupta, et al. ∙ 9 ∙ share

read it
BeeTrace: A Unified Platform for Secure Contact Tracing that Breaks Data Silos

Contact tracing is an important method to control the spread of an infec...
07/05/2020 ∙ by Xiaoyuan Liu, et al. ∙ 0 ∙ share

read it
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

We introduce three new robustness benchmarks consisting of naturally occ...
06/29/2020 ∙ by Dan Hendrycks, et al. ∙ 5 ∙ share

read it
Towards practical differentially private causal graph discovery

Causal graph discovery refers to the process of discovering causal relat...
06/15/2020 ∙ by Lun Wang, et al. ∙ 0 ∙ share

read it
Imitation Attacks and Defenses for Black-box Machine Translation Systems

We consider an adversary looking to steal or attack a black-box machine ...
04/30/2020 ∙ by Eric Wallace, et al. ∙ 0 ∙ share

read it
Epione: Lightweight Contact Tracing with Strong Privacy

Contact tracing is an essential tool in containing infectious diseases s...
04/28/2020 ∙ by Ni Trieu, et al. ∙ 0 ∙ share

read it
Pretrained Transformers Improve Out-of-Distribution Robustness

Although pretrained Transformers such as BERT achieve high accuracy on i...
04/13/2020 ∙ by Dan Hendrycks, et al. ∙ 0 ∙ share

read it
Anomalous Instance Detection in Deep Learning: A Survey

Deep Learning (DL) is vulnerable to out-of-distribution and adversarial ...
03/16/2020 ∙ by Saikiran Bulusu, et al. ∙ 8 ∙ share

read it
Proceedings of the AAAI-20 Workshop on Intelligent Process Automation (IPA-20)

This is the Proceedings of the AAAI-20 Workshop on Intelligent Process A...
01/15/2020 ∙ by Dell Zhang, et al. ∙ 0 ∙ share

read it
Hierarchical Variational Imitation Learning of Control Programs

Autonomous agents can learn by imitating teacher demonstrations of the i...
12/29/2019 ∙ by Roy Fox, et al. ∙ 17 ∙ share

read it
Synthetic Datasets for Neural Program Synthesis

The goal of program synthesis is to automatically generate programs in a...
12/27/2019 ∙ by Richard Shin, et al. ∙ 21 ∙ share

read it
Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients...
12/10/2019 ∙ by Peter Kairouz, et al. ∙ 33 ∙ share

read it
A Benchmark for Anomaly Segmentation

Detecting out-of-distribution examples is important for safety-critical ...
11/25/2019 ∙ by Dan Hendrycks, et al. ∙ 26 ∙ share

read it
REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data

Deep neural networks (DNNs) have achieved tremendous success in various ...
11/17/2019 ∙ by Xinyun Chen, et al. ∙ 0 ∙ share

read it
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

This paper studies model-inversion attacks, in which the access to a mod...
11/17/2019 ∙ by Yuheng Zhang, et al. ∙ 6 ∙ share

read it
An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms

This paper focuses on valuating training data for supervised learning ta...
11/17/2019 ∙ by Ruoxi Jia, et al. ∙ 14 ∙ share

read it
Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy

Outlier detection and novelty detection are two important topics for ano...
11/16/2019 ∙ by Min Du, et al. ∙ 14 ∙ share

read it
Duet: An Expressive Higher-order Language and Linear Type System for Statically Enforcing Differential Privacy

During the past decade, differential privacy has become the gold standar...
09/05/2019 ∙ by Joseph P. Near, et al. ∙ 0 ∙ share

read it
Data Capsule: A New Paradigm for Automatic Compliance with Data Privacy Regulations

The increasing pace of data collection has led to increasing awareness o...
08/30/2019 ∙ by Lun Wang, et al. ∙ 0 ∙ share

read it
Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms

Given a data set D containing millions of data points and a data consume...
08/22/2019 ∙ by Ruoxi Jia, et al. ∙ 11 ∙ share

read it
TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems

A trojan backdoor is a hidden pattern typically implanted in a deep neur...
08/02/2019 ∙ by Wenbo Guo, et al. ∙ 3 ∙ share

read it
Keystone: An Open Framework for Architecting TEEs

Trusted execution environments (TEEs) are being used in all the devices ...
07/23/2019 ∙ by Dayeol Lee, et al. ∙ 0 ∙ share

read it
Keystone: A Framework for Architecting TEEs

Trusted execution environments (TEEs) are becoming a requirement across ...
07/23/2019 ∙ by Dayeol Lee, et al. ∙ 0 ∙ share

read it
Characterizing Attacks on Deep Reinforcement Learning

Deep reinforcement learning (DRL) has achieved great success in various ...
07/21/2019 ∙ by Chaowei Xiao, et al. ∙ 4 ∙ share

read it
Natural Adversarial Examples

We introduce natural adversarial examples -- real-world, unmodified, and...
07/16/2019 ∙ by Dan Hendrycks, et al. ∙ 6 ∙ share

read it
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

Self-supervision provides effective representations for downstream tasks...
06/28/2019 ∙ by Dan Hendrycks, et al. ∙ 5 ∙ share

read it
Impossibility of Full Decentralization in Permissionless Blockchains

Bitcoin uses blockchain technology and proof-of-work (PoW) mechanism whe...
05/13/2019 ∙ by Yujin Kwon, et al. ∙ 0 ∙ share

read it
How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning

Machine learning has been widely applied to various applications, some o...
04/24/2019 ∙ by Xinlei Pan, et al. ∙ 20 ∙ share

read it
SysML: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
03/29/2019 ∙ by Alexander Ratner, et al. ∙ 0 ∙ share

read it
Towards Efficient Data Valuation Based on the Shapley Value

"How much is my data worth?" is an increasingly common question posed by...
02/27/2019 ∙ by Ruoxi Jia, et al. ∙ 17 ∙ share

read it
Sanctorum: A lightweight security monitor for secure enclaves

Enclaves have emerged as a particularly compelling primitive to implemen...
12/27/2018 ∙ by Ilia Lebedev, et al. ∙ 0 ∙ share

read it
Data Poisoning Attack against Unsupervised Node Embedding Methods

Unsupervised node embedding methods (e.g., DeepWalk, LINE, and node2vec)...
10/30/2018 ∙ by Mingjie Sun, et al. ∙ 4 ∙ share

read it
Assessing Generalization in Deep Reinforcement Learning

Deep reinforcement learning (RL) has achieved breakthrough results on ma...
10/29/2018 ∙ by Charles Packer, et al. ∙ 10 ∙ share

read it
Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation

Deep Neural Networks (DNNs) have been widely applied in various recognit...
10/11/2018 ∙ by Chaowei Xiao, et al. ∙ 0 ∙ share

read it
Characterizing Audio Adversarial Examples Using Temporal Dependency

Recent studies have highlighted adversarial examples as a ubiquitous thr...
09/28/2018 ∙ by Zhuolin Yang, et al. ∙ 2 ∙ share

read it

Dawn Song

Featured Co-authors