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.In this work, we systematically characterize and investigate membership and memorization privacy risks inherent in six LLM KD techniques.Using instruction-tuning settings that span seven NLP tasks, together with three teacher model families (GPT-2, LLAMA-2, and OPT), and various size student models, we demonstrate that all existing LLM KD approaches carry membership and memorization privacy risks from the teacher to its students.However, the extent of privacy risks varies across different KD techniques.We systematically analyse how key LLM KD components (KD objective functions, student training data and NLP tasks) impact such privacy risks.We also demonstrate a significant disagreement between memorization and membership privacy risks of LLM KD techniques.Finally, we characterize per-block privacy risk and demonstrate that the privacy risk varies across different blocks by a large margin.

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 capture the complexity and ambiguity encountered by security engineers in practice. We introduce SEC-bench, the first fully automated benchmarking framework for evaluating LLM agents on authentic security engineering tasks. SEC-bench employs a novel multi-agent scaffold that automatically constructs code repositories with harnesses, reproduces vulnerabilities in isolated environments, and generates gold patches for reliable evaluation. Our framework automatically creates high-quality software vulnerability datasets with reproducible artifacts at a cost of only $0.87 per instance. Using SEC-bench, we implement two critical software security tasks to rigorously evaluate LLM agents' capabilities: proof-of-concept (PoC) generation and vulnerability patching. A comprehensive evaluation of state-of-the-art LLM code agents reveals significant performance gaps, achieving at most 18.0% success in PoC generation and 34.0% in vulnerability patching on our complete dataset. These results highlight the crucial steps needed toward developing LLM agents that are more practical, intelligent, and autonomous for security engineering.

Language models have recently been applied to binary analysis tasks, such as function similarity detection and function signature recovery. These models typically employ a two-stage training process: pre-training via Masked Language Modeling (MLM) on machine code and fine-tuning for specific tasks. While MLM helps to understand binary code structures, it ignores essential code characteristics, including control and data flow, which negatively affect model generalization. Recent work leverages domain-specific features (e.g., control flow graphs and dynamic execution traces) in transformer-based approaches to improve binary code semantic understanding. This approach, however, involves complex feature engineering, a cumbersome and time-consuming process that can introduce predictive uncertainty when dealing with stripped or obfuscated code, which leads to a performance drop. We introduce PROTST, a novel transformer-based methodology for binary code embedding. PROTST employs a hierarchical training process based on a unique tree-like structure, where knowledge progressively flows from fundamental tasks at the root to more specialized tasks at the leaves. This progressive teacher-student paradigm allows the model to build upon previously learned knowledge, resulting in high-quality embeddings that can be effectively leveraged for diverse downstream binary analysis tasks. The effectiveness of PROTST is evaluated in seven binary analysis tasks, demonstrating an average of 14.8% improvement in F1 and MRR compared to traditional two-stage training, and a 16.6 % improvement when analyzing obfuscated code.

An advanced control strategy of a variable flux vernier reluctance machine is proposed to improve efficiency and load capacity in this paper. Distinguished with traditional vernier machines, this machine has a novel doubly salient structure with DC field-exciting windings in stator slots. Losses of this machine are produced in both three-phase armature windings and DC windings, which occasionally leads to low efficiency. In response, a loss-minimizing control strategy for the purpose of increasing efficiency in the whole speed range is proposed. Mathematical equations of this machine, including voltage equations and flux linkage equations, are presented based on synchronously rotating dq-axis coordinate system. The control strategy in high speed situation is also presented. The results of simulation in MATLAB SIMULINK are illustrated in this paper, where the effectiveness of the control strategy is proved by comparing the efficiency of this machine with traditional control strategy and with loss-minimizing control strategy.