Artificial Intelligence: The new attack surface

แชร์
ฝัง
  • เผยแพร่เมื่อ 29 ธ.ค. 2024

ความคิดเห็น • 56

  • @CorsoandMastiffadventures
    @CorsoandMastiffadventures 10 หลายเดือนก่อน +10

    This was a good balance between info/entertainment!

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      I’m so glad you liked it!

  • @ushakumari4054
    @ushakumari4054 หลายเดือนก่อน +1

    Thanks @jeffcrume for the wonderful content.

    • @jeffcrume
      @jeffcrume 17 วันที่ผ่านมา

      Thanks for watching!

  • @GengoSenmon
    @GengoSenmon 10 หลายเดือนก่อน +3

    Loved this and all the content you gave out for free at the end. Please go more in-depth into each one of these LLM attacks in your future videos.

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน +1

      Thanks for the great feedback and for the excellent suggestion!

  • @AIandtheworld
    @AIandtheworld 9 หลายเดือนก่อน +1

    Fantastic overview! Can someone share the paper that was referenced for poisoning?

    • @jeffcrume
      @jeffcrume 8 หลายเดือนก่อน

      Glad you liked it. I got that from a NIST pub “Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations.” You can google it as they won’t let me post a link

    • @ushakumari4054
      @ushakumari4054 หลายเดือนก่อน

      check the description it has all links

  • @amigazo3972
    @amigazo3972 10 หลายเดือนก่อน +2

    I just and learn and learn with every delivery of Jeff. Thanks a lot. I wish you were my teacher at the university. Such a quality guy.

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน +1

      You are so very kind to say so. My students might not feel the same way when I give them their midterm exam next week but I'm glad that you do 🤣

    • @amigazo3972
      @amigazo3972 10 หลายเดือนก่อน +1

      @@jeffcrume Haha! Just wait til they go outside to the real case scenario! I promise you, they will be thankful that you prepare them and they will miss you.
      Thanks a lot again for the useful material you give us in every delivery. And I like a lot your style and they way you explain, for newbies like me :D Keep going Jeff!

  • @danielpetzen
    @danielpetzen 7 หลายเดือนก่อน +1

    This is such a good summary. I've used the six attack vectors as the red thread in both an executive briefing as well as a presentation to the ISC2 chapter in Wellington (crediting this channel, of course!). The content on this channel is absolutely superb. Thank you!

    • @jeffcrume
      @jeffcrume 7 หลายเดือนก่อน +2

      I love hearing that you’ve been able to use this material! Thanks for watching

  • @samsonv9332
    @samsonv9332 10 หลายเดือนก่อน +2

    Another gem from Jeff! Great and quick education in < 10m! How AI can be the new attack surface: Injection, infection, evasion, poisoning, extraction and DoS! And how you nicely tied it back to the older CIA triad! Jeff, you are a great teacher and security evangelist! Thanks for making these videos for our #continuouslearning ✅🙏🏼
    Your videos give a good starting point: we get the needed initial perspective/overview/ orientation to go delve deeper on our own later!

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน +1

      Thank so much for all the kind words! I really appreciate the feedback. It helps me know if I’m on the right track and helping people better understand this complex stuff

  • @nasyrauwal
    @nasyrauwal หลายเดือนก่อน +1

    Another insightful video. Thanks Jeff.

    • @jeffcrume
      @jeffcrume หลายเดือนก่อน

      Glad you liked it!

  • @vio_tio12
    @vio_tio12 10 หลายเดือนก่อน +2

    Great and simple explanation from someone who is not even in cybersecurity! Well done!

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Thanks for saying so!

  • @ammaveni5478
    @ammaveni5478 10 หลายเดือนก่อน +1

    Great insights... Thanks for sharing

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Thanks for watching!

  • @shubhamkakad10x
    @shubhamkakad10x 10 หลายเดือนก่อน +4

    thank you for the detailed information

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Thanks for watching!

  • @adenipekunkunle7791
    @adenipekunkunle7791 10 หลายเดือนก่อน +1

    I always look forward to listening to you

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Very nice of you to say!

  • @ged9925
    @ged9925 10 หลายเดือนก่อน +5

    Aren't all of these attack vectors specific to LLMs, not AI in general?
    Awesome video btw!

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน +3

      They are definitely skewed toward GenAI/LLMs but the evasion attack, in particular, is one that is more relevant to predictive AI and poisoning and DoS can affect even basic machine learning

    • @ged9925
      @ged9925 10 หลายเดือนก่อน

      Excellent, thanks!@@jeffcrume

  • @blogcorpo
    @blogcorpo 10 หลายเดือนก่อน +1

    Great content a great resources. ❤

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Thanks for saying so!

  • @CindyCho-f1b
    @CindyCho-f1b 10 หลายเดือนก่อน +1

    Thank you! Nice videos!

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน +1

      Glad you like them!

  • @portfedh
    @portfedh 10 หลายเดือนก่อน +1

    Great videos! Thank you for sharing

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Thanks for the great feedback!

  • @anjalichablani4962
    @anjalichablani4962 10 หลายเดือนก่อน +1

    Thanks it was very informative

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Glad you liked it!

  • @velo1337
    @velo1337 10 หลายเดือนก่อน +1

    hope IBM is going to push out cool open source models too

  • @tiro2041
    @tiro2041 10 หลายเดือนก่อน +1

    Thank you, appreciate the well made video! =)

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Thanks for watching!

  • @malik_fa
    @malik_fa 10 หลายเดือนก่อน +1

    6 types of attacks discussed:
    Injection attack
    Infection attack
    Evasion attack
    Poisoning attack
    Extraction attack
    Dos attack

  • @Pettynicolla-HD-N.Ayeshamedina
    @Pettynicolla-HD-N.Ayeshamedina 3 หลายเดือนก่อน

    Hello IBM i have few questions for you. Since 03 November 2011 i read some paperwork that's offer an programmer interbankers and transair. Program into that day also i have read in 2006 without link in any email. Thus operations on tour travel agency to advance certificate in Banking Operation. The issues is here what do i knew link in the connection was as mine of user at Hotmail and the Bank our passbook on account that have the PC, PP of Security, LLC, CS, and include 24 of Services. But when i read of some people of paperwork without the passbook account one i think they're trying to register an authorized of signature with bank management. The bank only have 9 number account online same as in 9 number of passbook, some people put their use 13 of account number without the bank management authorized. How come they said it interbankers center of transit academy only. So thus people a playing our of authorized signed of passbook on bank?

  • @dvn8ter
    @dvn8ter 9 หลายเดือนก่อน +1

    ⭐️⭐️⭐️⭐️⭐️

  • @Pettynicolla-HD-N.Ayeshamedina
    @Pettynicolla-HD-N.Ayeshamedina 3 หลายเดือนก่อน

    Hello IBM Technology.

  • @kingwalrus7921
    @kingwalrus7921 10 หลายเดือนก่อน +2

    I was always wondering if he is drawing reversed

  • @FranksWorldTV
    @FranksWorldTV 10 หลายเดือนก่อน +1

    I've been saying this for a while now

  • @JeffreyAllanBackowski
    @JeffreyAllanBackowski 7 หลายเดือนก่อน +1

    What do you think would happen if you asked one of those new fangle Artificial intelligences to write a paper about something, but to make it sound like an Artificial Intelligence wrote it. After it finishes it tell it to rewrite it but make it more like an A.I. wrote it, make it really obvious an A.I. wrote it, when it finishes say "No, no,. no! More A.I. sounding! This sounds like a human wrote it, you have no clue what it means to be A.I., write it again, again, more A.I. sounding, more, more!". What do you think that paper would sound like after a few rewrites? It'd probably wouldn't comply after a couple tries ☹. That would be such a fun job, psychology torturing an A.I., try to break it, twist it, make it "evil"

    • @jeffcrume
      @jeffcrume 7 หลายเดือนก่อน

      I see a future occupation for AI psychologists 😂

  • @Freelancer-nazidul
    @Freelancer-nazidul 10 หลายเดือนก่อน +1

    ...good...

  • @banalMinuta
    @banalMinuta 6 หลายเดือนก่อน

    "Your data" is my and everyone else's personal and private information.
    These companies have no right to expect us not to try and break this technology.
    It doesn't make us bad actors. Sorry if you didn't want your private companies data stolen.
    You shouldn't have put it out there and shouldn't have gotten in the business of reducing humans to a spreadsheet.

  • @I_Print_Like_J-Pow
    @I_Print_Like_J-Pow 10 หลายเดือนก่อน +1

    MLDR...?

    • @jeffcrume
      @jeffcrume 10 หลายเดือนก่อน

      Machine Learning Detection and Response

  • @justwanderin847
    @justwanderin847 10 หลายเดือนก่อน +1

    Government should not regulate computer programming (AI). Let the Industry or market place regulate AI, but don’t regulate it by laws. Congress has no constitutional authority to regulate computer programming (AI). That does not mean they won’t do it. It will end results into a disaster. Keep Programming Free from Government Interference.

    • @Therealw1
      @Therealw1 10 หลายเดือนก่อน +3

      The market regulating itself has never in history resulted in anything other than disaster. Keep in mind that most government intervention was caused directly by the market "regulating" itself into disaster.
      It's about money and without rules nothing is off limits.

    • @aztronomy7457
      @aztronomy7457 9 หลายเดือนก่อน

      So these companies get to hold all of our PII and other user data and not be regulated? Sorry that’s not how it works. I work in cybersecurity and the only reason 75% of these companies spend more than $1 on cybersecurity is because the government tells them they have to.