KEN: Kernel Extensions using Natural Language

• URL: http://arxiv.org/abs/2312.05531v1
• Date: Sat, 9 Dec 2023 10:45:54 GMT
• Title: KEN: Kernel Extensions using Natural Language
• Authors: Yusheng Zheng, Yiwei Yang, Maolin Chen, Andrew Quinn
• Abstract summary: KEN is a framework that allows Kernel Extensions to be written in Natural language. It synthesizes an eBPF program given a user's English language prompt. We show that KEN produces correct eBPF programs on 80% which is an improvement of a factor of 2.67 compared to an LLM-empowered program synthesis baseline.
• Score: 1.293634133244466
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The ability to modify and extend an operating system is an important feature for improving a system's security, reliability, and performance. The extended Berkeley Packet Filters (eBPF) ecosystem has emerged as the standard mechanism for extending the Linux kernel and has recently been ported to Windows. eBPF programs inject new logic into the kernel that the system will execute before or after existing logic. While the eBPF ecosystem provides a flexible mechanism for kernel extension, it is difficult for developers to write eBPF programs today. An eBPF developer must have deep knowledge of the internals of the operating system to determine where to place logic and cope with programming limitations on the control flow and data accesses of their eBPF program enforced by the eBPF verifier. This paper presents KEN, an alternative framework that alleviates the difficulty of writing an eBPF program by allowing Kernel Extensions to be written in Natural language. KEN uses recent advances in large language models (LLMs) to synthesize an eBPF program given a user's English language prompt. To ensure that LLM's output is semantically equivalent to the user's prompt, KEN employs a combination of LLM-empowered program comprehension, symbolic execution, and a series of feedback loops. KEN's key novelty is the combination of these techniques. In particular, the system uses symbolic execution in a novel structure that allows it to combine the results of program synthesis and program comprehension and build on the recent success that LLMs have shown for each of these tasks individually. To evaluate KEN, we developed a new corpus of natural language prompts for eBPF programs. We show that KEN produces correct eBPF programs on 80% which is an improvement of a factor of 2.67 compared to an LLM-empowered program synthesis baseline.

Related papers

• Large Language Models are Interpretable Learners [53.56735770834617]
  In this paper, we show a combination of Large Language Models (LLMs) and symbolic programs can bridge the gap between expressiveness and interpretability. The pretrained LLM with natural language prompts provides a massive set of interpretable modules that can transform raw input into natural language concepts. As the knowledge learned by LSP is a combination of natural language descriptions and symbolic rules, it is easily transferable to humans (interpretable) and other LLMs.
  arXiv  Detail & Related papers  (2024-06-25T02:18:15Z)
• SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overhead [75.87007729801304]
  SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead. Experiments show that SpaFL improves accuracy while requiring much less communication and computing resources compared to sparse baselines.
  arXiv  Detail & Related papers  (2024-06-01T13:10:35Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• LILO: Learning Interpretable Libraries by Compressing and Documenting Code [71.55208585024198]
  We introduce LILO, a neurosymbolic framework that iteratively synthesizes, compresses, and documents code. LILO combines LLM-guided program synthesis with recent algorithmic advances in automated from Stitch. We find that AutoDoc boosts performance by helping LILO's synthesizer to interpret and deploy learned abstractions.
  arXiv  Detail & Related papers  (2023-10-30T17:55:02Z)
• Blind Evaluation Framework for Fully Homomorphic Encryption and Privacy-Preserving Machine Learning [0.0]
  Blind Evaluation Framework (BEF) is a cryptographically secure programming framework. It enables blind, but correct, execution of programming logic without Interactive Rounds of Decryption and Evaluation (IRDE) This is the first framework to enable both training and inference of machine learning models with FHE without decryption rounds.
  arXiv  Detail & Related papers  (2023-10-19T20:33:02Z)
• ANPL: Towards Natural Programming with Interactive Decomposition [33.58825633046242]
  We introduce an interactive ANPL system that ensures users can always refine the generated code. An ANPL program consists of a set of input-outputs that it must satisfy. The user revises an ANPL program by either modifying the sketch, changing the language used to describe the holes, or providing additional input-outputs to a particular hole.
  arXiv  Detail & Related papers  (2023-05-29T14:19:40Z)
• BRF: eBPF Runtime Fuzzer [3.895892630722353]
  This paper introduces the BPF Fuzzer (BRF), a fuzzer that can satisfy the semantics and dependencies required by the verifier and the eBPF subsystem. BRF achieves 101% higher code coverage. As a result, BRF has so far managed to find 4 vulnerabilities (some of them have been assigned runtime numbers) in the eBPF.
  arXiv  Detail & Related papers  (2023-05-15T16:42:51Z)
• MOAT: Towards Safe BPF Kernel Extension [10.303142268182116]
  The Linux kernel extensively uses the Berkeley Packet Filter (BPF) to allow user-written BPF applications to execute in the kernel space. Recent attacks show that BPF programs can evade security checks and gain unauthorized access to kernel memory. We present MOAT, a system that isolates potentially malicious BPF programs using Intel Memory Protection Keys (MPK)
  arXiv  Detail & Related papers  (2023-01-31T05:31:45Z)
• Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model [57.92200214957124]
  External language models (LMs) are used to improve the recognition performance of end-to-end (E2E) automatic speech recognition (ASR) systems. We propose a novel decoding algorithm where a word-level lattice is constructed on-the-fly to consider all possible word sequences. Our method consistently outperforms subword-level LMs, including N-gram LM and neural network LM.
  arXiv  Detail & Related papers  (2022-01-06T10:04:56Z)
• A Data-Centric Framework for Composable NLP Workflows [109.51144493023533]
  Empirical natural language processing systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components. We establish a unified open-source framework to support fast development of such sophisticated NLP in a composable manner.
  arXiv  Detail & Related papers  (2021-03-02T16:19:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.