Search Results - Bastounis, Alexander

  • Showing 1 - 12 results of 12
Refine Results
  1. 1
    How adversarial attacks can disrupt seemingly stable accurate classifiers

    How adversarial attacks can disrupt seemingly stable accurate classifiers by Sutton, Oliver J., Zhou, Qinghua, Tyukin, Ivan Y., Gorban, Alexander N., Bastounis, Alexander, Higham, Desmond J.

    Published in Neural networks
    Get full text
    Items that this one cites
    Article
    Save to List
    Saved in:
  2. 2
    The feasibility and inevitability of stealth attacks

    The feasibility and inevitability of stealth attacks by Tyukin, Ivan Y, Higham, Desmond J, Bastounis, Alexander, Woldegeorgis, Eliyas, Gorban, Alexander N

    Get full text
    Items that this one cites
    Article
    Save to List
    Saved in:
  3. 3
    How adversarial attacks can disrupt seemingly stable accurate classifiers

    How adversarial attacks can disrupt seemingly stable accurate classifiers by Sutton, Oliver J, Zhou, Qinghua, Tyukin, Ivan Y, Gorban, Alexander N, Bastounis, Alexander, Higham, Desmond J

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  4. 4
    The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning

    The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning by Bastounis, Alexander, Gorban, Alexander N, Hansen, Anders C, Higham, Desmond J, Prokhorov, Danil, Sutton, Oliver, Tyukin, Ivan Y, Zhou, Qinghua

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  5. 5
    When can you trust feature selection? -- I: A condition-based analysis of LASSO and generalised hardness of approximation

    When can you trust feature selection? -- I: A condition-based analysis of LASSO and generalised hardness of approximation by Bastounis, Alexander, Cucker, Felipe, Hansen, Anders C

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  6. 6
    When can you trust feature selection? -- II: On the effects of random data on condition in statistics and optimisation

    When can you trust feature selection? -- II: On the effects of random data on condition in statistics and optimisation by Bastounis, Alexander, Cucker, Felipe, Hansen, Anders C

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  7. 7
    The Feasibility and Inevitability of Stealth Attacks

    The Feasibility and Inevitability of Stealth Attacks by Tyukin, Ivan Y, Higham, Desmond J, Bastounis, Alexander, Eliyas Woldegeorgis, Gorban, Alexander N

    Published in arXiv.org
    Get full text
    Items that cite this one
    Article
    Save to List
    Saved in:
  8. 8
    The extended Smale's 9th problem -- On computational barriers and paradoxes in estimation, regularisation, computer-assisted proofs and learning

    The extended Smale's 9th problem -- On computational barriers and paradoxes in estimation, regularisation, computer-assisted proofs and learning by Bastounis, Alexander, Hansen, Anders C, Verner Vlačić

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  9. 9
    The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks

    The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks by Bastounis, Alexander, Hansen, Anders C, Verner Vlačić

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  10. 10
    On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know'

    On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know' by Bastounis, Alexander, Campodonico, Paolo, van der Schaar, Mihaela, Adcock, Ben, Hansen, Anders C

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  11. 11
    Stealth edits to large language models

    Stealth edits to large language models by Sutton, Oliver J, Zhou, Qinghua, Wang, Wei, Higham, Desmond J, Gorban, Alexander N, Bastounis, Alexander, Tyukin, Ivan Y

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  12. 12
    On the absence of the RIP in real-world applications of compressed sensing and the RIP in levels

    On the absence of the RIP in real-world applications of compressed sensing and the RIP in levels by Bastounis, Alexander, Hansen, Anders C

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:

Search Tools: