Search Results for author: Daniel Kang

Found 23 papers, 8 papers with code

NoScope: Optimizing Neural Network Queries over Video at Scale

1 code implementation7 Mar 2017 Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, Matei Zaharia

Given a target video, object to detect, and reference neural network, NoScope automatically searches for and trains a sequence, or cascade, of models that preserves the accuracy of the reference network but is specialized to the target video and are therefore far less computationally expensive.

Binary Classification

Q-Diffusion: Quantizing Diffusion Models

1 code implementation ICCV 2023 Xiuyu Li, Yijiang Liu, Long Lian, Huanrui Yang, Zhen Dong, Daniel Kang, Shanghang Zhang, Kurt Keutzer

We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture of the diffusion models, which compresses the noise estimation network to accelerate the generation process.

Image Generation Noise Estimation +1

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

1 code implementation17 Oct 2022 Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun

In this work, we present the first practical ImageNet-scale method to verify ML model inference non-interactively, i. e., after the inference has been done.

Retrieval SNARKS +1

Testing Robustness Against Unforeseen Adversaries

3 code implementations21 Aug 2019 Max Kaufmann, Daniel Kang, Yi Sun, Steven Basart, Xuwang Yin, Mantas Mazeika, Akul Arora, Adam Dziedzic, Franziska Boenisch, Tom Brown, Jacob Steinhardt, Dan Hendrycks

To narrow in on this discrepancy between research and reality we introduce ImageNet-UA, a framework for evaluating model robustness against a range of unforeseen adversaries, including eighteen new non-L_p attacks.

Adversarial Defense Adversarial Robustness

LIT: Learned Intermediate Representation Training for Model Compression

1 code implementation4 Sep 2019 Animesh Koratana, Daniel Kang, Peter Bailis, Matei Zaharia

In this work, we introduce Learned Intermediate representation Training (LIT), a novel model compression technique that outperforms a range of recent model compression techniques by leveraging the highly repetitive structure of modern DNNs (e. g., ResNet).

Image Classification Model Compression +2

Model Assertions for Monitoring and Improving ML Models

1 code implementation3 Mar 2020 Daniel Kang, Deepti Raghavan, Peter Bailis, Matei Zaharia

We propose methods of using model assertions at all stages of ML system deployment, including runtime monitoring, validating labels, and continuously improving ML models.

Active Learning

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

1 code implementation5 Mar 2024 Qiusi Zhan, Zhixiang Liang, Zifan Ying, Daniel Kang

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e. g., emails or websites).

Benchmarking Language Modelling +1

Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark

no code implementations4 Jun 2018 Cody Coleman, Daniel Kang, Deepak Narayanan, Luigi Nardi, Tian Zhao, Jian Zhang, Peter Bailis, Kunle Olukotun, Chris Re, Matei Zaharia

In this work, we analyze the entries from DAWNBench, which received optimized submissions from multiple industrial groups, to investigate the behavior of TTA as a metric as well as trends in the best-performing entries.

Benchmarking BIG-bench Machine Learning

LIT: Block-wise Intermediate Representation Training for Model Compression

no code implementations ICLR 2019 Animesh Koratana, Daniel Kang, Peter Bailis, Matei Zaharia

Knowledge distillation (KD) is a popular method for reducing the computational overhead of deep network inference, in which the output of a teacher model is used to train a smaller, faster student model.

Knowledge Distillation Model Compression

Model Specialization for Inference Via End-to-End Distillation, Pruning, and Cascades

no code implementations ICLR 2018 Daniel Kang, Karey Shi, Thao Ngyuen, Stephanie Mallard, Peter Bailis, Matei Zaharia

Thus, simply fine-tuning or transfer learn- ing from a general-purpose network inherits a large computational cost that may not be necessary for a given task.

General Classification Image Classification

Network Offloading Policies for Cloud Robotics: a Learning-based Approach

no code implementations15 Feb 2019 Sandeep Chinchali, Apoorva Sharma, James Harrison, Amine Elhafsi, Daniel Kang, Evgenya Pergament, Eyal Cidon, Sachin Katti, Marco Pavone

In this paper, we formulate a novel Robot Offloading Problem --- how and when should robots offload sensing tasks, especially if they are uncertain, to improve accuracy while minimizing the cost of cloud communication?

Decision Making object-detection +1

Transfer of Adversarial Robustness Between Perturbation Types

no code implementations3 May 2019 Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks, Jacob Steinhardt

We study the transfer of adversarial robustness of deep neural networks between different perturbation types.

Adversarial Robustness

Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference

no code implementations3 Jun 2019 Peter Kraft, Daniel Kang, Deepak Narayanan, Shoumik Palkar, Peter Bailis, Matei Zaharia

First, Willump automatically cascades feature computation for classification queries: Willump classifies most data inputs using only high-value, low-cost features selected through empirical observations of ML model performance, improving query performance by up to 5x without statistically significant accuracy loss.

BIG-bench Machine Learning

BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics

no code implementations2 May 2018 Daniel Kang, Peter Bailis, Matei Zaharia

We introduce two new query optimization techniques in BlazeIt that are not supported by prior work.

Databases

Improved Natural Language Generation via Loss Truncation

no code implementations ACL 2020 Daniel Kang, Tatsunori Hashimoto

In this work, we show that the distinguishability of the models and reference serves as a principled and robust alternative for handling invalid references.

Text Generation

Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics

no code implementations25 Jul 2020 Daniel Kang, Ankit Mathur, Teja Veeramacheneni, Peter Bailis, Matei Zaharia

This runtime engine a) efficiently pipelines preprocessing and DNN execution for inference, b) places preprocessing operations on the CPU or GPU in a hardware- and input-aware manner, and c) efficiently manages memory and threading for high throughput execution.

Proof: Accelerating Approximate Aggregation Queries with Expensive Predicates

no code implementations27 Jul 2021 Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Yi Sun, Matei Zaharia

Given a dataset $\mathcal{D}$, we are interested in computing the mean of a subset of $\mathcal{D}$ which matches a predicate.

Removing RLHF Protections in GPT-4 via Fine-Tuning

no code implementations9 Nov 2023 Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang

In tandem, LLM vendors have been increasingly enabling fine-tuning of their most powerful models.

LLM Agents can Autonomously Hack Websites

no code implementations6 Feb 2024 Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang

However, not much is known about the offensive capabilities of LLM agents.

Cannot find the paper you are looking for? You can Submit a new open access paper.