Educational platforms increasingly rely on vector databases to store and retrieve embedding representations of large-scale learning corpora (e.g., lecture notes, assignments, feedback, and student Q&A) for retrieval-augmented generation and analytics. However, directly indexing educational text embeddings raises privacy risks (student identities, sensitive performance signals, and protected attributes) and creates a management challenge: embeddings drift as curricula evolve, access policies change, and new content arrives continuously. This paper studies privacy-preserving intelligent management of educational-corpus vector libraries and proposes a novel, end-to-end algorithmic framework that jointly optimizes (i) privacy leakage control, (ii) retrieval quality, and (iii) operational efficiency under streaming updates. We introduce a hierarchical policy-aware vector lifecycle model, a privacy budget scheduler for adaptive re-embedding and re-indexing, and a secure-aware clustering-and-routing mechanism that supports fast query-time filtering with minimal accuracy loss. The resulting system, PP-EDUVec, enables compliant similarity search across multi-tenant educational data while automatically maintaining index health (freshness, redundancy, and utility) over time. On the EDU-Mix benchmark, PP-EDUVec achieves Recall@10 $=0.835$ while reducing representation leakage (LeakRep) from $0.215$ to $0.136$ ($-36.7\%$) and access-pattern leakage (LeakAP) from $0.398$ to $0.255$ ($-35.9\%$), and lowering mean latency from $42.1$ ms to $33.4$ ms ($-20.7\%$) and weekly maintenance time from $55.0$ to $35.8$ min/week ($-34.9\%$) compared with PostFilter.

This paper explores physical layer group key generation in wireless relay networks with a star topology. In this setup, the relay node plays the role of either a trusted or untrusted central node, while one legitimate node (Alice) acts as the reference node. The channel between the relay and Alice serves as the reference channel. To enhance security during the channel measurement stage, a cooperative jamming-based scheme is proposed in this paper. This scheme allows the relay to obtain superimposed channel observations from both the reference channel and other relay channels. Then, a public discussion is utilized to enable all nodes to obtain estimates of the reference channel. Subsequently, the legitimate nodes can agree on a secret key (SK) that remains secret from the eavesdropper (Eve), or a private key (PK) that needs to be secret from both the relay and Eve. This paper also derives the lower and upper bounds of the SK/PK capacity. Notably, it demonstrates that there exists only a small constant difference between the SK/PK upper and lower bounds in the high signal-to-noise ratio (SNR) regime. Simulation results confirm the effectiveness of the proposed scheme for ensuring security and efficiency of group key generation.

Personalized lesson planning is time-consuming and demands simultaneous alignment to curriculum standards, classroom constraints, and individual teacher style. Although large language models (LLMs) can draft lesson plans, their outputs often remain generic, lack verifiable grounding in official curricula, and require substantial teacher revision to become classroom-ready. We present TeachPlanAlign, a dual-profile lesson plan generation framework that (i) models both teacher preferences and class learning context, (ii) grounds generation in curriculum evidence through retrieval-augmented fine-tuning designed for open-book generation, and (iii) iteratively improves pedagogical coherence via a constraint-guided self-refinement loop. The framework produces structured plans with explicit time allocation, differentiation strategies, and an evidence-linked rationale that supports traceability to standards and instructional resources. We evaluate TeachPlanAlign on a multi-subject benchmark of lesson requests paired with curriculum documents and human-authored plans, and we further validate its usability through teacher-in-the-loop evaluation. Results show consistent improvements in curriculum alignment, evidence faithfulness, and teacher preference satisfaction, while reducing teacher editing effort. These findings suggest that dual-profile alignment with traceable curriculum grounding can improve the usability and auditability of LLM-based lesson planning on this benchmark, but they should not yet be interpreted as evidence of deployment readiness.

Large language models (LLMs) offer new opportunities for lesson planning, remediation, and personalized practice, but deploying them in real educational settings remains challenging for two reasons. First, direct use of learner interaction traces can expose sensitive information about student knowledge states and behavioral patterns. Second, unconstrained generation can produce recommendations that are pedagogically inconsistent with the adopted curriculum, such as skipping prerequisite concepts or drifting outside the prescribed textbook scope. We propose PrivPath, a stage–subject–textbook-aligned framework for privacy-preserving curriculum planning that explicitly separates on-device learner modeling from server-side content generation. Its core module, Tri-Index Private Path Planning (TIPP), first restricts planning to a scoped curriculum graph defined by the target educational context, then privatizes learner mastery summaries under local differential privacy before transmission, and finally computes a curriculum-feasible instructional path that is coupled with evidence-grounded constrained generation. This design preserves personalization while reducing reliance on raw student traces and improving controllability of the generated teaching sequence. Experiments on three educational interaction datasets paired with open-textbook curriculum graphs show that PrivPath substantially improves structural validity and privacy robustness. In particular, it raises graph feasibility from 82.5% to 99.2% relative to TriIndex-RAG, improves the offline pedagogical utility proxy $\Delta$AUC from 0.013 to 0.018, and lowers membership inference AUC from 0.74 to 0.52 at ${\epsilon }_{\mathrm{loc}}=1.0$. These results suggest that curriculum-aligned path planning, privacy-preserving learner adaptation, and practically useful LLM-based educational generation can be achieved within a unified framework.