Semi-automated protocol disambiguation and code generation

Yen, Jane; Lévai, Tamás; Ye, Qinyuan; Ren, Xiang; Govindan, Ramesh; Raghavan, Barath

doi:10.1145/3452296.3472910

Cited by 18 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Implementation Extraction. Yen et al [56] explored the use of NLP techniques to map RFCs to protocol implementations. To do this, they manually engineer an existing semantic parser to handle networking-specific vocabulary, and translate individual sentences to logical forms that can then be mapped to executable functions.…”

Section: Related Workmentioning

confidence: 99%

“…Canonical FSMs are created based not only on RFCs but also on input from experts with exposure to protocol implementations, and often also rely on analyzing the code [22], [57], [58]. RFCs contain ambiguities, unspecified behaviors that human experts solve in creating the Canonical FSM [16], [56], or simply missing information. Thus, unlike traditional NLP semantic parsing problems [59], [60], [24], which study methods for translating natural language into a complete formal representation, in our setting there is not a complete one-to-one translation between the text and the FSM.…”

Section: Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents

Pacheco¹,

Hippel²,

Weintraub³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automated attack discovery techniques, such as attacker synthesis or model-based fuzzing, provide powerful ways to ensure network protocols operate correctly and securely. Such techniques, in general, require a formal representation of the protocol, often in the form of a finite state machine (FSM). Unfortunately, many protocols are only described in English prose, and implementing even a simple network protocol as an FSM is time-consuming and prone to subtle logical errors. Automatically extracting protocol FSMs from documentation can significantly contribute to increased use of these techniques and result in more robust and secure protocol implementations.In this work we focus on attacker synthesis as a representative technique for protocol security, and on RFCs as a representative format for protocol prose description. Unlike other works that rely on rule-based approaches or use off-the-shelf NLP tools directly, we suggest a data-driven approach for extracting FSMs from RFC documents. Specifically, we use a hybrid approach consisting of three key steps: (1) large-scale word-representation learning for technical language, (2) focused zero-shot learning for mapping protocol text to a protocol-independent information language, and (3) rule-based mapping from protocol-independent information to a specific protocol FSM. We show the generalizability of our FSM extraction by using the RFCs for six different protocols: BGPv4, DCCP, LTP, PPTP, SCTP and TCP. We demonstrate how automated extraction of an FSM from an RFC can be applied to the synthesis of attacks, with TCP and DCCP as case-studies. Our approach shows that it is possible to automate attacker synthesis against protocols by using textual specifications such as RFCs.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Limitationsmentioning

confidence: 99%

Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents

Pacheco¹,

Hippel²,

Weintraub³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, thinking about synthesis in a broader sense, it is worth mentioning that similar formal methods have been used to programmatically (i) generate protocol code (but not configurations) from RFC requirements [25], and (ii) specifications from lower-level axiomatic requirements [26].…”

Section: Current State Of the Art In Network Configurationmentioning

confidence: 99%

“…Finally, we point out that relevant work targeting the synthesis of networkrelated software (but not network-related configurations) recently started to appear, with e.g., NLP techniques applied to text of IETF Request For Comments (RFC) normative documents for the sake of either auto-discovering and fixing ambiguities [42] or automatically generating protocol implementations [25].…”

Section: Code Synthesismentioning

confidence: 99%

Neural language models for network configuration: Opportunities and reality check

Houidi,

Rossi

2022

Preprint

View full text Add to dashboard Cite

Boosted by deep learning, natural language processing (NLP) techniques have recently seen spectacular progress, mainly fueled by breakthroughs both in representation learning with word embeddings (e.g. word2vec) as well as novel architectures (e.g. transformers). This success quickly invited researchers to explore the use of NLP techniques to other field, such as computer programming languages, with the promise to automate tasks in software programming (bug detection, code synthesis, code repair, cross language translation etc.). By extension, NLP has potential for application to network configuration languages as well, for instance considering tasks such as network configuration verification, synthesis, and cross-vendor translation. In this paper, we survey recent advances in deep learning applied to programming languages, for the purpose of code verification, synthesis and translation: in particularly, we review their training requirements and expected performance, and qualitatively assess whether similar techniques can benefit corresponding use-cases in networking.

show abstract

“…• Similarities of downstream tasks: First, similar to the status in NLP prior to the emergence of foundational models, specific solutions with their own preprocessing, features extraction, architectures, and datasets, are currently being developed for different tasks (e.g., congestion control [1,24,90], adaptive bitrate streaming [50], datacenter-scale automatic traffic optimization [7], job scheduling [31,51,51], resource management [65,91,99], network planning [104], packet classification [39], performance prediction [49], congestion prediction [56], performance estimation [100], malware detection [29,93], mapping from a low-quality video to a high-quality version [96], or semi-automated generation of protocol implementations from specification text [95].) Next, we observe that most of the underlying adopted machine learning approach behind those solutions (e.g., classification, anomaly detection, generator, and reinforcement learning) are areas where foundational models have been successfully applied, or being explored (Section 3.1).…”

Section: Introductionmentioning

confidence: 99%

Rethinking data-driven networking with foundation models

Le¹,

Srivatsa²,

Ganti³

et al. 2022

Proceedings of the 21st ACM Workshop on Hot Topics in Networks

View full text Add to dashboard Cite

Foundational models have caused a paradigm shift in the way artificial intelligence (AI) systems are built. They have had a major impact in natural language processing (NLP), and several other domains, not only reducing the amount of required labeled data or even eliminating the need for it, but also significantly improving performance on a wide range of tasks. We argue foundation models can have a similar profound impact on network traffic analysis, and management. More specifically, we show that network data shares several of the properties that are behind the success of foundational models in linguistics. For example, network data contains rich semantic content, and several of the networking tasks (e.g., traffic classification, generation of protocol implementations from specification text, anomaly detection) can find similar counterparts in NLP (e.g., sentiment analysis, translation from natural language to code, out-of-distribution). However, network settings also present unique characteristics and challenges that must be overcome. Our contribution is in highlighting the opportunities and challenges at the intersection of foundation models and networking.

show abstract

Semi-automated protocol disambiguation and code generation

Cited by 18 publications

References 36 publications

Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents

Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents

Neural language models for network configuration: Opportunities and reality check

Rethinking data-driven networking with foundation models

Contact Info

Product

Resources

About