← Search

Hanxiao Lu

2 accepted papers

2025

Membership and Memorization in LLM Knowledge Distillation

EMNLP 2025

Recent advances in Knowledge Distillation (KD) aim to mitigate the high computational demands of Large Language Models (LLMs) by transferring knowledge from a large ”teacher” to a smaller ”student” model. However, students may inherit the teacher’s privacy when the teacher is trained on private data

Cited by 0SourcePDFScholar
2025

SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks

NeurIPS 2025poster

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic challenges or simplified vulnerability datasets that fail to c…

Cited by 0SourcecodeScholar