Ruoxi Jia

Orcid: 0000-0001-9662-9556

Affiliations:
  • Virginia Tech, Blacksburg, VA, USA
  • University of California at Berkeley, Berkeley, CA, USA (PhD 2018)


According to our database1, Ruoxi Jia authored at least 87 papers between 2014 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study.
CoRR, 2024

A Safe Harbor for AI Evaluation and Red Teaming.
CoRR, 2024

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes.
CoRR, 2024

Efficient Data Shapley for Weighted Nearest Neighbor Algorithms.
CoRR, 2024

How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.
CoRR, 2024

2023
Variance reduced Shapley value estimation for trustworthy data valuation.
Comput. Oper. Res., November, 2023

Certifiably Robust Neural ODE With Learning-Based Barrier Function.
IEEE Control. Syst. Lett., 2023

Who Leaked the Model? Tracking IP Infringers in Accountable Federated Learning.
CoRR, 2023

Data Acquisition: A New Frontier in Data-centric AI.
CoRR, 2023

Learning to Rank for Active Learning via Multi-Task Bilevel Optimization.
CoRR, 2023

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
CoRR, 2023

Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation.
CoRR, 2023

Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models.
CoRR, 2023

LAVA: Data Valuation without Pre-Specified Learning Algorithms.
CoRR, 2023

A Randomized Approach for Tight Privacy Accounting.
CoRR, 2023

A Note on "Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms".
CoRR, 2023

A Note on "Towards Efficient Data Valuation Based on the Shapley Value".
CoRR, 2023

Meta-Sift: How to Sift Out a Clean Subset in the Presence of Data Poisoning?
Proceedings of the 32nd USENIX Security Symposium, 2023

ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms.
Proceedings of the 32nd USENIX Security Symposium, 2023

PrivMon: A Stream-Based System for Real-Time Privacy Attack Detection for Machine Learning Models.
Proceedings of the 26th International Symposium on Research in Attacks, 2023

A Randomized Approach to Tight Privacy Accounting.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Privacy-Friendly Approach to Data Valuation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Learning-to-Learn to Guide Random Search: Derivative-Free Meta Blackbox Optimization on Manifold.
Proceedings of the Learning for Dynamics and Control Conference, 2023

2D-Shapley: A Framework for Fragmented Data Valuation.
Proceedings of the International Conference on Machine Learning, 2023

Revisiting Data-Free Knowledge Distillation with Poisoned Teachers.
Proceedings of the International Conference on Machine Learning, 2023

Towards Robustness Certification Against Universal Perturbations.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

LAVA: Data Valuation without Pre-Specified Learning Algorithms.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information.
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

Data Banzhaf: A Robust Data Valuation Framework for Machine Learning.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Robust Data Valuation via Variance Reduced Data Shapley.
CoRR, 2022

Private Data Valuation and Fair Payment in Data Marketplaces.
CoRR, 2022

How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
CoRR, 2022

Data Banzhaf: A Data Valuation Framework with Maximal Robustness to Learning Stochasticity.
CoRR, 2022

QEKD: Query-Efficient and Data-Free Knowledge Distillation from Black-box Models.
CoRR, 2022

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models.
CoRR, 2022

Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Selective Differential Privacy for Language Modeling.
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

Adversarial Unlearning of Backdoors via Implicit Hypergradient.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Label-Only Model Inversion Attacks via Boundary Repulsion.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing.
Proc. Priv. Enhancing Technol., 2021

Stability-Based Analysis and Defense against Backdoor Attacks on Edge Computing Services.
IEEE Netw., 2021

Learning to Refit for Convex Learning Problems.
CoRR, 2021

Adversarial Unlearning of Backdoors via Implicit Hypergradient.
CoRR, 2021

Zero-Round Active Learning.
CoRR, 2021

Learnability of Learning Performance and Its Application to Data Valuation.
CoRR, 2021

A Unified Framework for Task-Driven Data Quality Management.
CoRR, 2021

One-Round Active Learning.
CoRR, 2021

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective.
Proceedings of the 9th International Conference on Learning Representations, 2021

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Knowledge-Enriched Distributional Model Inversion Attacks.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification?
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data.
Proceedings of the ASIA CCS '21: ACM Asia Conference on Computer and Communications Security, 2021

Improving Robustness to Model Inversion Attacks via Mutual Information Regularization.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
A Principled Approach to Data Valuation for Federated Learning.
Proceedings of the Federated Learning - Privacy and Incentive, 2020

Improved Techniques for Model Inversion Attacks.
CoRR, 2020

A Principled Approach to Data Valuation for Federated Learning.
CoRR, 2020

Private Distributed Mean Estimation.
CoRR, 2020

On the Impact of Perceptual Compression on Deep Learning.
Proceedings of the 3rd IEEE Conference on Multimedia Information Processing and Retrieval, 2020

Robust anomaly detection and backdoor attack detection via differential privacy.
Proceedings of the 8th International Conference on Learning Representations, 2020

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms.
Proc. VLDB Endow., 2019

An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms.
CoRR, 2019

Towards Efficient Data Valuation Based on the Shapley Value.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
Accountable Data Fusion and Privacy Preservation Techniques in Cyber-Physical Systems.
PhD thesis, 2018

A Framework for Privacy-Preserving Data Publishing with Enhanced Utility for Cyber-Physical Systems.
ACM Trans. Sens. Networks, 2018

Design Automation for Smart Building Systems.
Proc. IEEE, 2018

One Bit Matters: Understanding Adversarial Examples as the Abuse of Redundancy.
CoRR, 2018

The Helmholtz Method: Using Perceptual Compression to Reduce Machine Learning Complexity.
CoRR, 2018

Poisoning Attacks on Data-Driven Utility Learning in Games.
Proceedings of the 2018 Annual American Control Conference, 2018

2017
Virtual Occupancy Sensing: Using Smart Meters to Indicate Your Presence.
IEEE Trans. Mob. Comput., 2017

Privacy-preserving building-related data publication using PAD.
Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments, 2017

PAD: protecting anonymity in publishing building related datasets.
Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments, 2017

Privacy-enhanced architecture for occupancy-based HVAC Control.
Proceedings of the 8th International Conference on Cyber-Physical Systems, 2017

Optimal sensor-controller codesign for privacy in dynamical systems.
Proceedings of the 56th IEEE Annual Conference on Decision and Control, 2017

Towards a theory of free-lunch privacy in cyber-physical systems.
Proceedings of the 55th Annual Allerton Conference on Communication, 2017

2016
MapSentinel: Can the Knowledge of Space Use Improve Indoor Tracking Further?
Sensors, 2016

2015
A fully unsupervised non-intrusive load monitoring framework.
Proceedings of the 2015 IEEE International Conference on Smart Grid Communications, 2015

Poster Abstract: MapSentinel: Map-Aided Non-intrusive Indoor Tracking in Sensor-Rich Environments.
Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, 2015

SoundLoc: Accurate room-level indoor localization using acoustic signatures.
Proceedings of the IEEE International Conference on Automation Science and Engineering, 2015

2014
SoundLoc: Acoustic Method for Indoor Localization without Infrastructure.
CoRR, 2014

PresenceSense: zero-training algorithm for individual presence detection based on power monitoring.
Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, 2014

Environmental sensing by wearable device for indoor activity and location estimation.
Proceedings of the IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society, Dallas, TX, USA, October 29, 2014


  Loading...