papers

Publications (9)

cs.CR2017

Proof of Luck: an Efficient Blockchain Consensus Protocol

Mitar Milutinovic, Warren He, Howard Wu +1

In the paper, we present designs for multiple blockchain consensus primitives and a novel blockchain system, all based on the use of trusted execution environments (TEEs), such as…

cs.CR2019

Generating Adversarial Examples with Adversarial Networks

Chaowei Xiao, Bo Li, Jun-Yan Zhu +3

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mi…

cs.AI2026

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility

Xiaoyuan Liu, Jianhong Tu, Yuqi Chen +26

Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, cr…

cs.LG2022

Characterizing Attacks on Deep Reinforcement Learning

Xinlei Pan, Chaowei Xiao, Warren He +8

Recent studies show that Deep Reinforcement Learning (DRL) models are vulnerable to adversarial attacks, which attack DRL models by adding small perturbations to the observations.…

cs.CR2018

Spatially Transformed Adversarial Examples

Chaowei Xiao, Jun-Yan Zhu, Bo Li +3

Recent studies show that widely used deep neural networks (DNNs) are vulnerable to carefully crafted adversarial examples. Many advanced algorithms have been proposed to generate a…

cs.LG2017

Exploring the Space of Black-box Attacks on Deep Neural Networks

Arjun Nitin Bhagoji, Warren He, Bo Li +1

Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "t…

cs.LG2017

Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong

Warren He, James Wei, Xinyun Chen +2

Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a stron…

cs.CR2021

Do I Get the Privacy I Need? Benchmarking Utility in Differential Privacy Libraries

Gonzalo Munilla Garrido, Joseph Near, Aitsam Muhammad +3

An increasing number of open-source libraries promise to bring differential privacy to practice, even for non-experts. This paper studies five libraries that offer differentially p…

cs.CR2019

Ekiden: A Platform for Confidentiality-Preserving, Trustworthy, and Performant Smart Contract Execution

Raymond Cheng, Fan Zhang, Jernej Kos +6

Smart contracts are applications that execute on blockchains. Today they manage billions of dollars in value and motivate visionary plans for pervasive blockchain deployment. While…