Konrad Rieck

@mlsec

Professor of Computer Science, Institute of System Security, TU Braunschweig

Brunswick, Germany
Vrijeme pridruživanja: prosinac 2009.

Tweetovi

Blokirali ste korisnika/cu @mlsec

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @mlsec

  1. proslijedio/la je Tweet
    prije 24 sata
    Odgovor korisnicima

    You've missed a real opportunity for snark here, e.g. like this one from Tibshirani

    Poništi
  2. proslijedio/la je Tweet

    The biggest difference between statistics and machine learning may be in language! So a few months ago I created this (inspired by ) but haven't made much progress since. Welcoming suggestions for improvements

    Poništi
  3. proslijedio/la je Tweet
    5. velj

    Unsere Jubiläumsfahne hängt! 🎉 Freut Euch auf den Campustag, Ausstellungen, Konzerte, Licht-Installationen und noch viel mehr! ➡️

    Poništi
  4. proslijedio/la je Tweet
    3. velj

    This news reminds me of the European Space Agency in saying that "human beings" usually cannot "access flying spacecraft" so "there is no need for side channel attack protection". Serious attackers build machines to carry out attacks beyond human ability.

    Poništi
  5. 3. velj

    Congratulations! 🍾🎉 Another group of brave students passed our practical course on learning-based security systems

    Poništi
  6. proslijedio/la je Tweet
    3. velj

    We’ve extended the deadline for our ICLR workshop on trustworthy ML to February 12th AoE. The CFP is below. Cc

    Poništi
  7. proslijedio/la je Tweet
    31. sij

    155b polymorphic execve(/bin/sh) ELF64 base64 -d <<< f0VMRmoBWUiJ57He60aQkAIAPgABAAAABAAAAAEAAAAcAAAAAAAAAAAAAAAAAAAAAQAAAEAAOAABAAIAAgAAAAAAAAACAAAAAAAAAAIAAAAAAAAAxwQkSO8MlsdEJARl8fG8x0QkCLew8a3HRCQMtpYfNcdEJBDWjZZXx0QkFDmOiZbHRCQYVzhu5cdEJBzR2wAAgDQP3uL6/+c= >p;chmod +x p;./p

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    28. sij

    Over the years I've seen old pictures of the moving desks of the Central Social Institution of Prague, but I had no idea they were still in use.

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet

    Das wichtigste Interview des Jahres - auf einer schweizer Seite, ⁦⁩ ⁦⁩ ⁦⁩ ...

    Poništi
  10. proslijedio/la je Tweet
    27. sij

    This year it took us a little while longer, but of course we are going to have another great workshop at 2020 🙃 You find the here:

    Poništi
  11. proslijedio/la je Tweet
    27. sij

    Being Chinese in America

    Poništi
  12. proslijedio/la je Tweet
    26. sij

    Protip: If your deep neural network won’t converge, try remodulating the shield frequencies and reconfiguring the plasma relay to emit a rapid EM burst directly at the subspace anomaly.

    Poništi
  13. proslijedio/la je Tweet
    25. sij

    Die erste korrekte Zuordnung der Fußreflexzonen.

    Poništi
  14. proslijedio/la je Tweet
    22. sij

    In the 1970-80's, AI was all about "computational models of mental processes". With the advent of ML, many now view AI as "algorithmic replacement of mental processes". We lost something in this transition, b/c the fun part of doing AI is gaining an understanding of ourselves.

    Poništi
  15. proslijedio/la je Tweet
    24. sij

    Tips and tricks for hackers. Submissions encouraged! thc-1001-tips-and-tricks/README.md at master · hackerschoice/thc-1001-tips-and-tricks · GitHub

    Poništi
  16. proslijedio/la je Tweet
    23. sij

    Few highlights: * The number of submissions is back on the exponential curve * It's becoming more and more common for researchers to serve in all PCs in the same year * International collaborations are on the rise. China in particular is growing very fast!

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    20. sij
    Poništi
  18. proslijedio/la je Tweet
    15. sij

    In a new paper, we literally "make war mean peace". Our attack on AI perturbs corpora to change word “meanings” that get encoded in vector embeddings like . With , Yoav Meri, Vitaly Shmatikov. To appear at IEEE S&P

    Poništi
  19. proslijedio/la je Tweet
    20. sij

    Is this a sales pitch addressing threat actors or is it good offensive research because threat actors could do this as well - some day in the future of an alternative universe?

    Poništi
  20. proslijedio/la je Tweet
    18. sij

    ACM is thinking about how citations should appear in computer science papers. Current citations use author-year format. Some find it verbose. Prev poll had vote splitting—let's try ranking options instead: (RT if you care about this issue)

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·