Publications

Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang
Preprint

LLM Agents can Autonomously Exploit One-day Vulnerabilities
Richard Fang, Rohan Bindu, Akul Gupta, Daniel Kang
Preprint

Trustless Audits without Revealing Data or Models
Suppakit Waiwitlikhit, Ion Stoica, Yi Sun, Tatsunori Hashimoto, Daniel Kang
ICML (2024)

ZKML: An Optimizing System for ML Inference in Zero-Knowledge Proofs
Bing-Jyue Chen, Suppakit Waiwitlikhit, Ion Stoica, Daniel Kang
EuroSys 2024

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
Qiusi Zhan, Zhixiang Liang, Zifan Ying, Daniel Kang
ACL findings (2024)

A Safe Harbor for AI Evaluation and Red Teaming
ICML (2024)

LLM Agents can Autonomously Hack Websites
Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang
Preprint

Identifying and Mitigating the Security Risks of Generative AI
Foundations and Trends in Privacy and Security

Dias: Dynamic Rewriting of Pandas Code
Stefanos Baziotis, Daniel Kang, Charith Mendis
SIGMOD 2024

Removing RLHF Protections in GPT-4 via Fine-Tuning
Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang
NAACL 2024

Q-Diffusion: Quantizing Diffusion Models
Xiuyu Li, Yijiang Liu, Long Lian, Huanrui Yang, Zhen Dong, Daniel Kang, Shanghang Zhang, Kurt Keutzer
ICCV 2023

Accelerating Aggregation Queries on Unstructured Streams of Data
Matthew Russo, Tatsunori Hashimoto, Daniel Kang, Yi Sun, Matei Zaharia
VLDB 2023

Do hospitals that participate in COVID-19 research differ from non-trial hospitals? A cross-sectional study of US hospitals
Daniel Kang, Cher Huang, Alexander Yuen, Keith Norris, Tara Vijayan
Trials

Data Management for ML-based Analytics and Beyond
Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Matei Zaharia
ACM Journal of Data Science 2023

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, Tatsunori Hashimoto
ICML AdvML Frontiers Workshop (2023)

ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation
Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun
Preprint

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun
NeurIPS RegulateML Workshop (2023)

Optimizing Video Analytics with Declarative Model Relationships
Francisco Romero, Johann Hauswald, Aditi Partap, Daniel Kang, Matei Zaharia, Christos Kozyrakis
VLDB 2023

Efficient and Accurate Systems for Querying Unstructured Data
Daniel Kang
Thesis

Semantic Indexes for Machine Learning-based Queries over Unstructured Data
Daniel Kang*, John Guibas*, Peter Bailis, Tatsunori Hashimoto, Matei Zaharia
SIGMOD 2022

Finding Label and Model Errors in Perception Data With Learned Observation Assertions
Daniel Kang, Nikos Arechiga, Sudeep Pillai, Peter Bailis, Matei Zaharia
SIGMOD 2022, AIDB (VLDB workshop) 2021, NeurIPS DCAI workshop 2021

VIVA: An End-to-End System for Interactive Video Analytics
Daniel Kang*, Francisco Romero*, Peter Bailis, Christos Kozyrakis, Matei Zaharia
CIDR 2022

Exploiting Proximity Search and Easy Examples to Select Rare Events
Daniel Kang, Alex Derhacobian, Kaoru Tsuji, Trevor Hebert, Peter Bailis, Tadashi Fukami, Tatsunori Hashimoto, Yi Sun, Matei Zaharia
NeurIPS DCAI workshop 2021

Accelerating Approximate Aggregation Queries with Expensive Predicates
Daniel Kang*, John Guibas*, Peter Bailis, Tatsunori Hashimoto, Yi Sun, Matei Zaharia
VLDB 2021 (extended technical report)

Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
Daniel Kang, Ankit Mathur, Teja Veeramacheneni, Peter Bailis, Matei Zaharia
VLDB 2021

Approximate Selection with Guarantees using Proxies
Daniel Kang*, Edward Gan*, Peter Bailis, Tatsunori Hashimoto, Matei Zaharia
VLDB 2020

A Demonstration of Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Peter Kraft, Daniel Kang, Deepak Narayanan, Shoumik Palkar, Peter Bailis, Matei Zaharia VLDB 2020 demo

Improved Natural Language Generation via Loss Truncation
Daniel Kang, Tatsunori Hashimoto
ACL 2020

Model Assertions for Improving and Monitoring ML Models
Daniel Kang*, Deepti Raghavan*, Peter Bailis, Matei Zaharia
MLSys 2020

Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Peter Kraft, Daniel Kang, Deepak Narayanan, Shoumik Palkar, Peter Bailis, Matei Zaharia
MLSys 2020

MLPerf Training Benchmark
MLSys 2020

BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics
Daniel Kang, Peter Bailis, Matei Zaharia
VLDB 2020

Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
Cody Coleman*, Daniel Kang*, Deepak Narayanan*, Luigi Nardi, Tian Zhao, Jian Zhang, Peter Bailis, Kunle Olukotun, Chris Ré, Matei Zaharia
ACM SIGOPS OSR 2019

LIT: Learned Intermediate Representation Training for Model Compression
Animesh Koratana*, Daniel Kang*, Peter Bailis, Matei Zaharia
ICML 2019

Challenges and Opportunities in DNN-Based Video Analytics: A Demo of the BlazeIt Video Query Engine
Daniel Kang, Peter Bailis, Matei Zaharia
CIDR 2019

Model Assertions for Debugging Machine Learning
Daniel Kang*, Deepti Raghavan*, Peter Bailis, Matei Zaharia
NeurIPS MLSys Workshop 2018, Contributed Talk
ICLR DebugML Workshop 2019, Best student research paper, Contributed talk

Analysis of the Time-To-Accuracy Metric and Entries in the DAWNBench Deep Learning Benchmark
Cody Coleman*, Deepak Narayanan*, Daniel Kang*, Tian Zhao, Jian Zhang, Luigi Nardi, Peter Bailis, Kunle Olukotun, Chris Ré, and Matei Zaharia
NeurIPS MLSys Workshop 2018

Block-wise Intermediate Representation Training for Model Compression
Animesh Koratana*, Daniel Kang*, Peter Bailis, Matei Zaharia
NeurIPS CDNNRIA Workshop 2018

BlazeIt: An Optimizing Query Engine for Video at Scale
Daniel Kang, Peter Bailis, Matei Zaharia
SysML 2018

NoScope: Optimizing Neural Network Queries over Video at Scale
Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, Matei Zaharia
PVLDB 2017

DAWNBench: An End-to-End Deep Learning Benchmark and Competition
Cody Coleman, Deepak Narayanan, Daniel Kang, Tian Zhao, Jian Zhang, Luigi Nardi, Peter Bailis, Kunle Olukotun, Chris Ré, and Matei Zaharia
NIPS ML Systems Workshop 2017, Contributed Talk

A synergistic DNA logic predicts genome-wide chromatin accessibility
Tatsunori Hashimoto*, Richard I. Sherwood*, Daniel Kang*, Nisha Rajagopal, Amira Barkal, Haoyang Zeng, Bart Emons, Sharanya Srinivasan, Tommi Jaakkola, David Gifford
Genome Research (2016)

GERV: a statistical method for generative evaluation of regulatory variants for transcription factor binding
Haoyang Zeng, Tatsunori Hashimoto, Daniel Kang, David Gifford
Bioinformatics (2016)

Non-trapping surfaces of revolution with long-living resonances
Kiril Datchev, Daniel Kang, Andre Kessler
Mathematical Research Letters (2015)