Profiles2022-2026
Lan Zhang
University of Science and Technology of China
12Papers
2Last author
14Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers12
- STIP: Three-Party Privacy-Preserving and Lossless Inference for Large Transformers in ProductionAuthor 2 of 6NDSS 2026 · 2 citations
- Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy OptimizationAuthor 9 of 10ICML 2026 · 1 citation
- How Do LLMs "Trust" Unknown Knowledge? An Unknown Knowledge Based Jailbreak AttackAuthor 2 of 3ACL Findings 2026
- Untraceable DeepFakes via Traceable Fingerprint EliminationAuthor 2 of 6ICLR 2026
- RemoteRAG: A Privacy-Preserving LLM Cloud RAG ServiceAuthor 2 of 5ACL Findings 2025 · 16 citations
- Exploiting Task-Level Vulnerabilities: An Automatic Jailbreak Attack and Defense Benchmarking for LLMsAuthor 1 of 5USENIX Security 2025
- Model Lineage Closeness AnalysisAuthor 2 of 5AAAI 2025
- Safety Layers in Aligned Large Language Models: The Key to LLM SecurityAuthor 3 of 4ICLR 2025
- PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at ScaleAuthor 2 of 2SIGCOMM 2023 · 18 citations
- Optimal Arms Identification with KnapsacksAuthor 2 of 5ICML 2023 · 5 citations
- PCAT: Functionality and Data Stealing from Split Learning by Pseudo-Client AttackAuthor 2 of 2USENIX Security 2023
- MLink: Linking Black-Box Models for Collaborative Multi-Model InferenceAuthor 2 of 3AAAI 2022 · 10 citations
