Jason Trost

@jason_trost

Interests: Network security, Digital Forensics, Machine Learning, Big Data. retweets are not endorsements.

Atlanta, GA
covert.io
Vrijeme pridruživanja: ožujak 2010.
128 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @jason_trost

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

  1. proslijedio/la je Tweet
    prije 23 sata

    v0.2 of my security learning model thanks to feedback from and . It's part of what makes security so exhilarating that many conversations (e.g. strategy around designing a threat response operation) require every layer as part of the conversation.

    3 proslijeđena tweeta 19 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    4. velj

    There is a new AI, ML, & Data Science track for USA this year. If you are doing offensive ML research, we want to see it!

    32 proslijeđena tweeta 58 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    4. velj

    1/ Some thoughts on the way ML gets talked about in security: Most security problems are not machine learning problems. Like encryption, dual-factor authentication, taint analysis, or hand-crafted IOCs, machine learning is just one of many security tools.

    10 proslijeđenih tweetova 43 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    20. sij

    Heterogeneous Information Networks and Applications to Cyber Security

    2 proslijeđena tweeta 3 korisnika označavaju da im se sviđa
    Poništi
  5. 3. velj

    3 Short Links on Popular Domain Lists for Threat Intelligence

    1 proslijeđeni tweet 5 korisnika označava da im se sviđa
    Poništi
  6. 3. velj

    6 Short Links on Malware Training Set Creation for Machine Learning

    5 proslijeđenih tweetova 14 korisnika označava da im se sviđa
    Poništi
  7. 3. velj

    Collecting and Curating IOC Whitelists for Threat Intelligence and Machine Learning Research

    3 proslijeđena tweeta 14 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    31. sij

    Facial Recognition meets malware clustering: training on family names plus some embedding tricks stolen from the FR literature plus TSNE leads to super sharp clusters, with a few cases of potential mislabeling to dig into (check out the potential FNs southeast of the origin)!

    5 proslijeđenih tweetova 18 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    29. sij
    Odgovor korisnicima i sljedećem broju korisnika:

    What % of malware uses non-TLS vs TLS for C2? Based on a (super biased) sample of ~10k binaries over 10 years I estimate it’s 90/10. Would love to see someone do a broader, less biased eval to see if it is on the rise (I don’t think it is)

    6 replies 41 proslijeđeni tweet 76 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    27. sij

    . recently decommissioned their Adversary Tactics: course, and rather than let it collect dust, they offered it up to the community for free in the spirit of their commitment to transparency.

    66 proslijeđenih tweetova 160 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    28. sij

    1\ Surprisingly, you could build a very mediocre PE malware detector with a single PE feature: the PE compile timestamp. In fact, I built a little random forest detector that uses only the timestamp as its feature that gets 62% detection on previously unseen malware at a 1% FPR.

    6 replies 133 proslijeđena tweeta 333 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. 28. sij

    Robustness of AI Systems Against Adversarial Attacks

    3 proslijeđena tweeta 1 korisnik označava da mu se sviđa
    Poništi
  13. proslijedio/la je Tweet
    27. sij

    OSINT thread inbound. I did this all on my phone from the dog park. This ones for Starting with nothing, this is the pic. Going for an explicit pin, not just the "location". Let's build some data points. First - Identifiable landmarks, front to back 1/x

    OSINT me, where did I take this photo? Try to pin it 🤷‍♂️
    25 replies 340 proslijeđenih tweetova 1.171 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    26. sij

    1\ Let's bypass a convolutional neural network trained to recognize previously unseen bad URLs. The classifier gives a score between 0 (benign) and 1 (definitely malicious). I start by making up a phishing URL: hxxp://wellsfargo-customer-support.webhosting.pl/login

    1 reply 7 proslijeđenih tweetova 30 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    24. sij

    1/ Here's a thread on how to build the kind of security artifact "social network" graph popularized by and others, but customized, and on your own private security data. Consider the following graph, where the nodes are malware samples:

    1 reply 21 proslijeđeni tweet 30 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    24. sij

    Debugging deep learning models can be really tricky and frustrating, especially in the security space where a lot of the time you're not sure about ground truth labels, but here's a thread with some tricks I've picked up. Add your own if you've got them! 1/

    11 proslijeđenih tweetova 33 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 27. sij

    HeadPrint: Detecting Anomalous Communications through Header-based Application Fingerprinting

    5 proslijeđenih tweetova 14 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    26. sij

    The claim in the FTI forensics report on Bezos’ iPhone that, “due to end-to-end encryption employed by WhatsApp, it is virtually impossible to decrypt the contents of the downloader [.enc file]...” bugged me so much that I coded up how to do it:

    1.182 proslijeđena tweeta 2.771 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    23. sij

    Checkout the latest revision:

    presenting very thorough and original work on inferring descriptions of malware samples' purposes, via a deep neural net. . Work done jointly with , , , and AI.
    2 proslijeđena tweeta 4 korisnika označavaju da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    23. sij

    presenting very thorough and original work on inferring descriptions of malware samples' purposes, via a deep neural net. . Work done jointly with , , , and AI.

    1 proslijeđeni tweet 2 korisnika označavaju da im se sviđa
    Poništi

@jason_trost još nije objavio nijedan Tweet.

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:

    ·