Jinyuan Jia

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE Security and Privacy, 2024

TextGuard: Provable Defense against Backdoor Attacks on Text Classification.

[BibT_eX]

[DOI]

Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

SHINE: Shielding Backdoors in Deep Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Graph Neural Network Explanations are Fragile.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Certifiably Robust Image Watermark.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Data Poisoning Based Backdoor Attacks to Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Towards General Robustness Verification of MaxPool-Based Convolutional Neural Networks via Tightening Linear Approximation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

MMCert: Provable Defense Against Adversarial Attacks to Multi-Modal Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Poster: Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the 19th ACM Asia Conference on Computer and Communications Security, 2024

POSTER: Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications.

[BibT_eX]

[DOI]

Proceedings of the 19th ACM Asia Conference on Computer and Communications Security, 2024

Jailbreak Open-Sourced Large Language Models via Enforced Decoding.

[BibT_eX]

[DOI]

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.

[BibT_eX]

[DOI]

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications.

[BibT_eX]

[DOI]

CoRR, 2023

Prompt Injection Attacks and Defenses in LLM-Integrated Applications.

[BibT_eX]

[DOI]

CoRR, 2023

On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?

[BibT_eX]

[DOI]

CoRR, 2023

PORE: Provably Robust Recommender Systems against Data Poisoning Attacks.

[BibT_eX]

[DOI]

Proceedings of the 32nd USENIX Security Symposium, 2023

FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information.

[BibT_eX]

[DOI]

Proceedings of the 44th IEEE Symposium on Security and Privacy, 2023

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning.

[BibT_eX]

[DOI]

Bhaskar Ramasubramanian

Bo Li

Radha Poovendran

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service.

[BibT_eX]

[DOI]

Wenjie Qu

Proceedings of the 30th Annual Network and Distributed System Security Symposium, 2023

Screen Perturbation: Adversarial Attack and Defense on Under-Screen Camera.

[BibT_eX]

[DOI]

Proceedings of the 29th Annual International Conference on Mobile Computing and Networking, 2023

Graph Contrastive Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Privacy Protection via Adversarial Examples.

[BibT_eX]

[DOI]

PhD thesis, 2022

FLCert: Provably Secure Federated Learning Against Poisoning Attacks.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2022

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning.

[BibT_eX]

[DOI]

CoRR, 2022

StolenEncoder: Stealing Pre-trained Encoders.

[BibT_eX]

[DOI]

CoRR, 2022

Poisoning Attacks to Local Differential Privacy Protocols for Key-Value Data.

[BibT_eX]

[DOI]

Proceedings of the 31st USENIX Security Symposium, 2022

PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the 31st USENIX Security Symposium, 2022

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning.

[BibT_eX]

[DOI]

Yupei Liu

Proceedings of the 43rd IEEE Symposium on Security and Privacy, 2022

MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples.

[BibT_eX]

[DOI]

Wenjie Qu

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients.

[BibT_eX]

[DOI]

Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 2022

Deep Neural Network Piration without Accuracy Loss.

[BibT_eX]

[DOI]

Krishnendu Chakrabarty

Proceedings of the 21st IEEE International Conference on Machine Learning and Applications, 2022

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022

Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

10 Security and Privacy Problems in Self-Supervised Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Stealing Links from Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 30th USENIX Security Symposium, 2021

Data Poisoning Attacks to Local Differential Privacy Protocols.

[BibT_eX]

[DOI]

Proceedings of the 30th USENIX Security Symposium, 2021

Backdoor Attacks to Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the SACMAT '21: The 26th ACM Symposium on Access Control Models and Technologies, 2021

Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation.

[BibT_eX]

[DOI]

Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

On the Intrinsic Differential Privacy of Bagging.

[BibT_eX]

[DOI]

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

Detection Of Malicious DNS and Web Servers using Graph-Based Approaches.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

PointGuard: Provably Robust 3D Point Cloud Classification.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the CCS '21: 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, Republic of Korea, November 15, 2021

Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes.

[BibT_eX]

[DOI]

Proceedings of the ASIA CCS '21: ACM Asia Conference on Computer and Communications Security, 2021

IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary.

[BibT_eX]

[DOI]

Proceedings of the ASIA CCS '21: ACM Asia Conference on Computer and Communications Security, 2021

Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Provably Secure Federated Learning against Malicious Clients.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Certified Robustness of Nearest Neighbors against Data Poisoning Attacks.

[BibT_eX]

[DOI]

CoRR, 2020

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing.

[BibT_eX]

[DOI]

CoRR, 2020

Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing.

[BibT_eX]

[DOI]

Proceedings of the WWW '20: The Web Conference 2020, Taipei, Taiwan, April 20-24, 2020, 2020

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the 29th USENIX Security Symposium, 2020

Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Defending Against Machine Learning Based Inference Attacks via Adversarial Examples: Opportunities and Challenges.

[BibT_eX]

[DOI]

Proceedings of the Adaptive Autonomous Secure Cyber Systems., 2020

2019

Structure-Based Sybil Detection in Social Networks via Local Rule-Based Propagation.

[BibT_eX]

[DOI]

IEEE Trans. Netw. Sci. Eng., 2019

Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges.

[BibT_eX]

[DOI]

CoRR, 2019

Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation.

[BibT_eX]

[DOI]

Proceedings of the 26th Annual Network and Distributed System Security Symposium, 2019

Calibrate: Frequency Estimation and Heavy Hitter Identification with Local Differential Privacy via Incorporating Prior Knowledge.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE Conference on Computer Communications, 2019

MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples.

[BibT_eX]

[DOI]

Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019

2018

AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning.

[BibT_eX]

[DOI]

Proceedings of the 27th USENIX Security Symposium, 2018

2017

AttriInfer: Inferring User Attributes in Online Social Networks Using Markov Random Fields.

[BibT_eX]

[DOI]

Proceedings of the 26th International Conference on World Wide Web, 2017

Random Walk Based Fake Account Detection in Online Social Networks.

[BibT_eX]

[DOI]