2021

MLDS: A Dataset for Weight-Space Analysis of Neural Networks

Clemens, John

Understand

Neural networks are powerful models that solve a variety of complex real-world problems.

  • However, the stochastic nature of training and large number of parameters in a typical neural model makes them difficult to evaluate via inspection.
  • Research shows this opacity can hide latent undesirable behavior, be it from poorly representative training data or via malicious intent to subvert the behavior of the network, and that this behavior is difficult to detect via traditional indirect evaluation criteria such as loss.
  • Therefore, it is time to explore direct ways to evaluate a trained neural model via its structure and weights.

Built on

  • Long short-term memory

    Sepp Hochreiter and Jürgen Schmidhuber · 1997

    Earlier work this paper cites.

  • High-performance task distribution for volunteer computing

    David Anderson, Eric Korpela, and Rom Walton · 2006

    Earlier work this paper cites.

  • Learning phrase representations using rnn encoder-decoder for statistical machine translation, 2014

    Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio · 2014

    Earlier work this paper cites.

  • Adam: A method for stochastic optimization, 2017

    Diederik P. Kingma and Jimmy Ba · 2017

    Earlier work this paper cites.

  • Model learning

    Frits Vaandrager · 2017

    Earlier work this paper cites.

Similar

  • Adversarial patch, 2018

    Tom B. Brown, Dandelion Mané, Aurko Roy, Martín Abadi, and Justin Gilmer · 2018

    Cited alongside, same era.

  • Learning device models with recurrent neural networks

    J. Clemens · 2018

    Cited alongside, same era.

  • BOINC: A platform for volunteer computing

    Original

    David P. Anderson · 2019

    Cited alongside, same era.

  • Badnets: Identifying vulnerabilities in the machine learning model supply chain, 2019

    Tianyu Gu, Brendan Dolan-Gavitt, and Siddharth Garg · 2019

    Cited alongside, same era.

  • Pytorch: An imperative style, high-performance deep learning library

    Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala · 2019

    Cited alongside, same era.

  • Kaggle: Your machine learning and data science community

    Cited in the paper.

Then

  • The trojai software framework: An opensource tool for embedding trojans into deep learning models, 2020

    Kiran Karra, Chace Ashcraft, and Neil Fendley · 2020

    Later among the works it cites.

  • Umap: Uniform manifold approximation and projection for dimension reduction, 2020

    Leland McInnes, John Healy, and James Melville · 2020

    Later among the works it cites.

  • Detecting ai trojans using meta neural analysis, 2020

    Xiaojun Xu, Qi Wang, Huichen Li, Nikita Borisov, Carl A. Gunter, and Bo Li · 2020

    Later among the works it cites.

  • Trojannet: Embedding hidden trojan horse models in neural networks, 2021

    Chuan Guo, Ruihan Wu, and Kilian Q. Weinberger · 2021

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…