Tianhang Zheng

Orcid: 0000-0002-5151-1527

According to our database¹, Tianhang Zheng authored at least 52 papers between 2017 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking.

[BibT_eX]

[DOI]

CoRR, May, 2026

RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry.

[BibT_eX]

[DOI]

CoRR, May, 2026

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs.

[BibT_eX]

[DOI]

CoRR, May, 2026

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training.

[BibT_eX]

[DOI]

CoRR, April, 2026

Mitigating Error Amplification in Fast Adversarial Training.

[BibT_eX]

[DOI]

CoRR, April, 2026

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models.

[BibT_eX]

[DOI]

CoRR, April, 2026

Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache.

[BibT_eX]

[DOI]

CoRR, March, 2026

MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety.

[BibT_eX]

[DOI]

CoRR, February, 2026

Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection.

[BibT_eX]

[DOI]

CoRR, January, 2026

DUALBREACH: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization.

[BibT_eX]

[DOI]

Proceedings of the 33rd Annual Network and Distributed System Security Symposium, 2026

MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Poisoning with a Pill: Circumventing Detection in Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

From Topology to Behavioral Semantics: Enhancing BGP Security by Understanding BGP's Language with LLMs.

[BibT_eX]

[DOI]

CoRR, November, 2025

Untargeted Jailbreak Attack.

[BibT_eX]

[DOI]

CoRR, October, 2025

Dynamic Target Attack.

[BibT_eX]

[DOI]

CoRR, October, 2025

HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment.

[BibT_eX]

[DOI]

CoRR, September, 2025

Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons.

[BibT_eX]

[DOI]

CoRR, June, 2025

DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization.

[BibT_eX]

[DOI]

CoRR, April, 2025

AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors.

[BibT_eX]

[DOI]

CoRR, January, 2025

Faithful Interpretation for Graph Neural Networks.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

Hurricane Mixer: The Eye in the Storm - Embedding Regulatory Oversight into Cryptocurrency Mixing Services.

[BibT_eX]

[DOI]

IACR Cryptol. ePrint Arch., 2025

Nearly Optimal Differentially Private ReLU Regression.

[BibT_eX]

[DOI]

Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

Contextual Bandits for Unbounded Context Distributions.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Fair Text-to-Image Diffusion via Fair Mapping.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

FLTracer: Accurate Poisoning Attack Provenance in Federated Learning.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2024

CMI: Client-Targeted Membership Inference in Federated Learning.

[BibT_eX]

[DOI]

Tianhang Zheng

Baochun Li

IEEE Trans. Dependable Secur. Comput., 2024

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services.

[BibT_eX]

[DOI]

CoRR, 2024

Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning.

[BibT_eX]

[DOI]

CoRR, 2024

Text Guided Image Editing with Automatic Concept Locating and Forgetting.

[BibT_eX]

[DOI]

CoRR, 2024

FedReview: A Review Mechanism for Rejecting Poisoned Updates in Federated Learning.

[BibT_eX]

[DOI]

Tianhang Zheng

Baochun Li

CoRR, 2024

Separable Multi-Concept Erasure from Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2024

2023

RDM-DC: Poisoning Resilient Dataset Condensation with Robust Distribution Matching.

[BibT_eX]

[DOI]

Tianhang Zheng

Baochun Li

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Be Careful with PyPI Packages: You May Unconsciously Spread Backdoor Model Weights.

[BibT_eX]

[DOI]

Tianhang Zheng

Hao Lan

Baochun Li

Proceedings of the Sixth Conference on Machine Learning and Systems, 2023

2022

On the Robustness of Metric Learning: An Adversarial Perspective.

[BibT_eX]

[DOI]

ACM Trans. Knowl. Discov. Data, 2022

Guided Erasable Adversarial Attack (GEAA) Toward Shared Data Protection.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2022

Poisoning Attacks on Deep Learning based Wireless Traffic Prediction.

[BibT_eX]

[DOI]

Tianhang Zheng

Baochun Li

Proceedings of the IEEE INFOCOM 2022, 2022

InfoCensor: An Information-Theoretic Framework against Sensitive Attribute Inference and Demographic Disparity.

[BibT_eX]

[DOI]

Tianhang Zheng

Baochun Li

Proceedings of the ASIA CCS '22: ACM Asia Conference on Computer and Communications Security, Nagasaki, Japan, 30 May 2022, 2022

2021

First-Order Efficient General-Purpose Clean-Label Data Poisoning.

[BibT_eX]

[DOI]

Tianhang Zheng

Baochun Li

Proceedings of the 40th IEEE Conference on Computer Communications, 2021

Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving?

[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

2020

Towards Assessment of Randomized Mechanisms for Certifying Adversarial Robustness.

[BibT_eX]

[DOI]

CoRR, 2020

Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition.

[BibT_eX]

[DOI]

CoRR, 2020

Learning-based Practical Smartphone Eavesdropping with Built-in Accelerometer.

[BibT_eX]

[DOI]

Proceedings of the 27th Annual Network and Distributed System Security Symposium, 2020

Accelerometer-based smartphone eavesdropping.

[BibT_eX]

[DOI]

Proceedings of the MobiCom '20: The 26th Annual International Conference on Mobile Computing and Networking, 2020

2019

Towards Data Poisoning Attack against Knowledge Graph Embedding.

[BibT_eX]

[DOI]

CoRR, 2019

FID: Function Modeling-based Data-Independent and Channel-Robust Physical-Layer Identification.

[BibT_eX]

[DOI]

Tianhang Zheng

Zhi Sun

Kui Ren

Proceedings of the 2019 IEEE Conference on Computer Communications, 2019

Data Poisoning Attack against Knowledge Graph Embedding.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

InverseNet: Solving Inverse Problems of Multimedia Data with Splitting Networks.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Multimedia and Expo, 2019

PointCloud Saliency Maps.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Distributionally Adversarial Attack.

[BibT_eX]

[DOI]

Tianhang Zheng

Changyou Chen

Kui Ren

Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018

Learning Saliency Maps for Adversarial Point-Cloud Generation.

[BibT_eX]

[DOI]

CoRR, 2018

2017

Data Independent Identification for Privacy Preservation.

[BibT_eX]

[DOI]

Tianhang Zheng

Zhi Sun

Kui Ren

Proceedings of the IEEE Symposium on Privacy-Aware Computing, 2017

Tianhang Zheng

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...