Publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
- Security
- AI / ML
- NLP
- Vision
- Systems & Networking
- Preprint
2026
-
NeurIPS 2026
MetaPI: Constructing Prompt Injection Benchmarks from Any Agent Benchmarks
In 40th Conference on Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026 -
arXiv 2026
From Docs to Descriptions: Smell-Aware Evaluation of MCP Server Descriptions
arXiv preprint, 2026 -
arXiv 2026
The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
arXiv preprint, 2026 -
ICLR 2026
TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
In ICLR, 2026 -
ACL 2026
Measuring Large Language Models’ Adversarial Behavior in Social Deduction GamesIn The 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026
-
ACL 2026
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language ModelsIn The 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026
-
arXiv 2026
Reframing LLM Agent Security as an Agent–Human Interaction Problem
In Arxiv, 2026 -
arXiv 2026
-
arXiv 2026
Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
2026
2025
-
AAAI 2025
Towards Adversarially Robust Condensed Dataset by Curvature Regularization
In The 39th Annual AAAI Conference on Artificial Intelligence, 2025 -
arXiv 2025
AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
arXiv preprint, 2025 -
TMLR 2025
Large Language Model-based Data Science Agent: A Survey
Transactions on Machine Learning Research, 2025 -
arXiv 2025
From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
arXiv preprint, 2025 -
arXiv 2025
What Are Models Thinking About? Understanding Large Language Model Hallucinations "Psychology" Through Model Inner State Analysis
arXiv preprint, 2025 -
ICCV 2025
Dataset Distillation via the Wasserstein Metric
In International Conference on Computer Vision, 2025 -
IJCAI 2025
Split-and-Privatize Framework for Large Language Model Fine-Tuning
In 34th International Joint Conference on Artificial Intelligence (IJCAI), 2025 -
INFOCOM 2025
FedUFD: Uncertainty-Driven Feature Distillation for Heterogeneous Federated Learning
In IEEE International Conference on Computer Communications (INFOCOM), 2025 -
NAACL 2025
RePD: Defending Jailbreak Attacks Through a Retrieval-based Prompt Decomposition ProcessIn 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, 2025
-
TPDS 2025
FedLoRE: Communication-Efficient and Personalized Edge Intelligence Framework via Federated Low-Rank Estimation
IEEE Transactions on Parallel and Distributed Systems, 2025
2024
-
CCS 2024
Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies
In 31st ACM Conference on Computer and Communications Security (CCS), 2024 🏆 CCS Distinguished Paper Award -
arXiv 2024
Astra: Efficient and Money-saving Automatic Parallel Strategies Search on Heterogeneous GPUs
arXiv preprint, 2024 -
arXiv 2024
DistDD: Distributed Data Distillation Aggregation Through Gradient Matching
arXiv preprint, 2024 -
arXiv 2024
Prompt Injection Benchmark for Foundation Model Integrated Systems
arXiv preprint, 2024 -
arXiv 2024
SecDT: Mitigating Label Leakage in Two-Party Split Learning
arXiv preprint, 2024 -
CIKM 2024
Distributed Boosting: An Enhancing Method on Dataset Distillation
In 33rd ACM International Conference on Information and Knowledge Management (CIKM), 2024
2023
-
arXiv 2023
DistPlanS: Automating Execution Planning for Distributed Deep Neural Networks
arXiv preprint, 2023 -
arXiv 2023
FedCliP: Federated Learning with Client Pruning
arXiv preprint, 2023 -
CNSM 2023
TinyG: Accurate IP Geolocation Using a Tiny Number of Probers
In 2023 19th International Conference on Network and Service Management, 2023 -
FGCS 2023
Top AS Router Geolocation in Databases: Performance and Techniques
Future Generation Computer Systems, 2023
2022
-
FGCS 2022
Defending Byzantine Attacks in Ensemble Federated Learning: A Reputation-based Phishing Approach
Future Generation Computer Systems, 2022
2021
-
CSE 2021
MineDetector: JavaScript Browser-side Cryptomining Detection Using Static Methods
In 2021 IEEE 24th International Conference on Computational Science and Engineering, 2021 -
GLOBECOM 2021
FedVANet: Efficient Federated Learning with Non-IID Data for Vehicular Ad Hoc Networks
In 2021 IEEE Global Communications Conference (GLOBECOM), 2021 -
ISCC 2021
FLPhish: Reputation-based Phishing Byzantine Defense in Ensemble Federated Learning
In 2021 IEEE Symposium on Computers and Communications (ISCC), 2021 🏆 Best Paper Award