Search Results for author: Ruoxi Sun

Found 28 papers, 10 papers with code

On Security Weaknesses and Vulnerabilities in Deep Learning Systems

1 code implementation12 Jun 2024 Zhongzheng Lai, Huaming Chen, Ruoxi Sun, Yu Zhang, Minhui Xue, Dong Yuan

In this work, we specifically look into deep learning (DL) framework and perform the first systematic study of vulnerabilities in DL systems through a comprehensive analysis of identified vulnerabilities from Common Vulnerabilities and Exposures (CVE) and open-source DL tools, including TensorFlow, Caffe, OpenCV, Keras, and PyTorch.

Chain of Agents: Large Language Models Collaborating on Long-Context Tasks

no code implementations4 Jun 2024 Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, Sercan Ö. Arik

Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs).

Code Completion Question Answering

Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training

no code implementations31 May 2024 Maximillian Chen, Ruoxi Sun, Sercan Ö. Arik, Tomas Pfister

Large language models (LLMs) aligned through reinforcement learning from human feedback (RLHF) have quickly become one of the dominant paradigms for building intelligent conversational assistant agents.

Machine Reading Comprehension Question Answering +1

Effective Large Language Model Adaptation for Improved Grounding and Citation Generation

no code implementations16 Nov 2023 Xi Ye, Ruoxi Sun, Sercan Ö. Arik, Tomas Pfister

Our framework tunes LLMs to selfground the claims in their responses and provide accurate citations to retrieved documents.

Language Modelling Large Language Model +2

RAI4IoE: Responsible AI for Enabling the Internet of Energy

no code implementations20 Sep 2023 Minhui Xue, Surya Nepal, Ling Liu, Subbu Sethuvenkatraman, Xingliang Yuan, Carsten Rudolph, Ruoxi Sun, Greg Eisenhauer

This paper plans to develop an Equitable and Responsible AI framework with enabling techniques and algorithms for the Internet of Energy (IoE), in short, RAI4IoE.


SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)

no code implementations26 May 2023 Ruoxi Sun, Sercan Ö. Arik, Alex Muzio, Lesly Miculicich, Satya Gundabathula, Pengcheng Yin, Hanjun Dai, Hootan Nakhost, Rajarishi Sinha, Zifeng Wang, Tomas Pfister

Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data.

Data Augmentation In-Context Learning +3

Universal Self-Adaptive Prompting

no code implementations24 May 2023 Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Hanjun Dai, Julian Martin Eisenschlos, Sercan O. Arik, Tomas Pfister

A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting.

In-Context Learning Natural Language Understanding +2

Better Zero-Shot Reasoning with Self-Adaptive Prompting

no code implementations23 May 2023 Xingchen Wan, Ruoxi Sun, Hanjun Dai, Sercan O. Arik, Tomas Pfister

Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans.

Neural Spline Search for Quantile Probabilistic Modeling

no code implementations12 Jan 2023 Ruoxi Sun, Chun-Liang Li, Sercan O. Arik, Michael W. Dusenberry, Chen-Yu Lee, Tomas Pfister

Accurate estimation of output quantiles is crucial in many use cases, where it is desired to model the range of possibility.

Attribute regression +2

The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices

1 code implementation23 Sep 2022 Wanlun Ma, Derui Wang, Ruoxi Sun, Minhui Xue, Sheng Wen, Yang Xiang

However, recent advanced backdoor attacks show that this assumption is no longer valid in dynamic backdoors where the triggers vary from input to input, thereby defeating the existing defenses.


M^4I: Multi-modal Models Membership Inference

1 code implementation15 Sep 2022 Pingyi Hu, Zihan Wang, Ruoxi Sun, Hu Wang, Minhui Xue

To achieve this, we propose Multi-modal Models Membership Inference (M^4I) with two attack methods to infer the membership status, named metric-based (MB) M^4I and feature-based (FB) M^4I, respectively.

Image Captioning Inference Attack +2

Does GNN Pretraining Help Molecular Representation?

no code implementations13 Jul 2022 Ruoxi Sun, Hanjun Dai, Adams Wei Yu

Extracting informative representations of molecules using Graph neural networks (GNNs) is crucial in AI-driven drug discovery.

Drug Discovery molecular representation

StyleFool: Fooling Video Classification Systems via Style Transfer

1 code implementation30 Mar 2022 Yuxin Cao, Xi Xiao, Ruoxi Sun, Derui Wang, Minhui Xue, Sheng Wen

In this paper, we focus on unrestricted perturbations and propose StyleFool, a black-box video adversarial attack via style transfer to fool the video classification system.

Adversarial Attack Classification +3

PublicCheck: Public Integrity Verification for Services of Run-time Deep Models

no code implementations21 Mar 2022 Shuo Wang, Sharif Abuadbba, Sidharth Agarwal, Kristen Moore, Ruoxi Sun, Minhui Xue, Surya Nepal, Seyit Camtepe, Salil Kanhere

Existing integrity verification approaches for deep models are designed for private verification (i. e., assuming the service provider is honest, with white-box access to model parameters).

Model Compression

Learning to Prompt for Continual Learning

4 code implementations CVPR 2022 Zifeng Wang, Zizhao Zhang, Chen-Yu Lee, Han Zhang, Ruoxi Sun, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, Tomas Pfister

The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge.

Class Incremental Learning Image Classification

Towards understanding retrosynthesis by energy-based models

no code implementations NeurIPS 2021 Ruoxi Sun, Hanjun Dai, Li Li, Steven Kearnes, Bo Dai

In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions.

Drug Discovery Retrosynthesis

Mate! Are You Really Aware? An Explainability-Guided Testing Framework for Robustness of Malware Detectors

1 code implementation19 Nov 2021 Ruoxi Sun, Minhui Xue, Gareth Tyson, Tian Dong, Shaofeng Li, Shuo Wang, Haojin Zhu, Seyit Camtepe, Surya Nepal

We find that (i) commercial antivirus engines are vulnerable to AMM-guided test cases; (ii) the ability of a manipulated malware generated using one detector to evade detection by another detector (i. e., transferability) depends on the overlap of features with large AMM values between the different detectors; and (iii) AMM values effectively measure the fragility of features (i. e., capability of feature-space manipulation to flip the prediction results) and explain the robustness of malware detectors facing evasion attacks.

Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography

no code implementations20 Jul 2021 Zihan Wang, Olivia Byrnes, Hu Wang, Ruoxi Sun, Congbo Ma, Huaming Chen, Qi Wu, Minhui Xue

The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding.

Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics

1 code implementation17 Sep 2020 Li Li, Stephan Hoyer, Ryan Pederson, Ruoxi Sun, Ekin D. Cubuk, Patrick Riley, Kieron Burke

Including prior knowledge is important for effective machine learning models in physics, and is usually achieved by explicitly adding loss terms or constraints on model architectures.

BIG-bench Machine Learning

Energy-based View of Retrosynthesis

no code implementations14 Jul 2020 Ruoxi Sun, Hanjun Dai, Li Li, Steven Kearnes, Bo Dai

Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery.

Drug Discovery Retrosynthesis +1

Scalable Bayesian inference of dendritic voltage via spatiotemporal recurrent state space models

no code implementations NeurIPS 2019 Ruoxi Sun, Ian Kinsella, Scott Linderman, Liam Paninski

However, current sensors and imaging approaches still face significant limitations in SNR and sampling frequency; therefore statistical denoising and interpolation methods remain critical for understanding single-trial spatiotemporal dendritic voltage dynamics.

Bayesian Inference Denoising

Scalable approximate Bayesian inference for particle tracking data

1 code implementation ICML 2018 Ruoxi Sun, Liam Paninski

This approach is therefore highly flexible and improves on the state of the art in terms of accuracy; provides uncertainty estimates about the particle locations and identities; and has a test run-time that scales linearly as a function of the data length and number of particles, thus enabling Bayesian inference in arbitrarily large particle tracking datasets.

Bayesian Inference

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