Great initiative. I've been trying to ramp up on this topic and this series came in handy. Thanks for sharing your knowledg.
@mehdis.74049 күн бұрын
As an example of rules creating dogma I'd like to mention the NNs case. If you pick any old (before 2012) neural nets book, you are being told that the rule of "no more than three layers of neural nets are needed", because of some math proof that three layers can approximate any function possible and that discouraged stacking up more layers as those may cause overfit or unncessary computing. And if we had followed that rule we would never have Deep Neural Networks we have today. I think that 3 layers rule was for long idleness in AI before AlexNet come along.
@Tesfamichael.G12 күн бұрын
This is a fantastic video! It offers a refreshing perspective on the importance of challenging established norms in computer engineering. Your insights on pushing boundaries and exploring unconventional approaches are truly inspiring. This video encourages a mindset of innovation and reminds us that groundbreaking advancements often come from questioning the status quo. Thank you for sharing!
@zilliard135224 күн бұрын
This was truly good, thank you Todd
@AmdetsionFekaduTemesgen26 күн бұрын
very interesting thank you, Professor Todd Austin!
@AmdetsionFekaduTemesgen26 күн бұрын
very interesting thank you, Professor Todd Austin!
@KimberlyHall-n2sАй бұрын
Thanks for the breakdown! Could you help me with something unrelated: My OKX wallet holds some USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). How can I transfer them to Binance?
@infinity2357_Ай бұрын
Thank you for sharing
@nathnaeldereje51272 ай бұрын
Thanks a lot, This was really useful.
@CyperSacurity3 ай бұрын
Thanks for the great content you provide..... can you please release these slides of every hardware security video in github repo? ... It will be very helpful.
@hahahaiiihu6 ай бұрын
Very interesting! Thank you professor!!
@FrederickAdom6 ай бұрын
Very insightful.
@victorcruceru32467 ай бұрын
buffer = read_input(); is a piece of odd C code. Probably incoorect. Better C code: read_code(&buffer[0]);
@bradrickrobinson74527 ай бұрын
Thank you for putting out these videos about the untold technology of hardware security. I'm currently going through the VETS-HASTE Program sponsored by Veterans Florida and University of Florida and your videos are most definitely shedding some light on the situation. My questions to you are: What is a typical day for a person in hardware security? How can you keep steady work in this type of technology field? Thanks again for all that you do!!!
@MallelaSitaramaChandrasekhar8 ай бұрын
Do you have a playlist for secure boot process, using the above knowledge ? Or any youtube links that have dealt with the secure boot fundamentals and its deployment in the industry ?
@braanajjar653011 ай бұрын
hi prof Todd, i am a jordanian student working on an archticure project and i need to use simplescaler tool version 3, but no matter how hard i search for, there are some files that i cant obtain such as simpleutils-990811.tar.gz and other files, the only file i can reach is simplesim-3.0 thanks to someone who archived it as a github repo, if you can point me to where i can obtain those files related to version 3, i would be very grateful professor
@patriciat.812111 ай бұрын
29:26
@neginmahani1406 Жыл бұрын
Todd, you're an absolute superstar! Your insights and teaching style shine brightly, inspiring countless minds like mine. Thank you for being such an exceptional mentor!
@porglezomp7235 Жыл бұрын
Hi Todd, I took EECS 370 a few years back, it was fun to see this video from you shared in a Rust slack channel at work. I’m curious how much existing LLVM-level mitigations help here, does adding `-C llvm-args='--x86-speculative-load-hardening'` to the compilation flags help thwart this already?
@canying0913 Жыл бұрын
I have watched this repetitively for about 6 months and it always calms me down whenever I am closer to mental meltdown due to up and downs on my research life. Thank you Professor Austin!
@prof.todd.austin Жыл бұрын
This comment made my week! Ty! I'm glad the video was helpful!
@ZaidEngComp Жыл бұрын
thanks for sharing , we appreciates if you share with us the materials
@neginmahani1406 Жыл бұрын
I really enjoyed the video, thanks, Tod!
@lovelymemes9179 Жыл бұрын
Thank you professor for your valuable insights!!
@mpetry912 Жыл бұрын
this is super interesting !
@srimanthtenneti6425 Жыл бұрын
This is really cool 👏
@LydellAaron Жыл бұрын
This was an awesome talk. Researcher tips and breaking rules in research style. What is the best way to access research papers as a civilian/non-student? Thank you!
@joelmandebi7212 Жыл бұрын
Another great discussion. Thanks Prof. Austin
@racim.boussa Жыл бұрын
Later i'll show you how to get past Rust 🔥🔥
@rohitmittal42 Жыл бұрын
When will you be completing the 6 videos
@prof.todd.austin Жыл бұрын
I'll be releasing new videos in the 6-part series at about 1 video every 3-4 days, please subscribe to this channel and KZbin will notify you when the later episodes go live. Thanks for watching!
@rohitmittal42 Жыл бұрын
Awesome. Thank you! I was always confused by security and privacy.
@junaidamjad5053 Жыл бұрын
Great explanation professor, I do have one question regarding producing the factors of a number originally from which the number was produced, is it really possible? Even if quantum computers gave us the computation power for doing all this computation but is not our solution space is infinite possible solution, so how do we find the exact factors which were used to produce the number in first place? I don't have knowledge of working of these ciphers so kindly do correct me if I'm approaching it in a wrong way, thanks.
@prof.todd.austin Жыл бұрын
Thanks for the question! The factoring solution space is not infinite, but it is exponential (or worse) with the number of bits in the keys. Here's an almost 2000 year old algorithm that will factor any number into its prime factors, given enough time to compute: en.wikipedia.org/wiki/Sieve_of_Eratosthenes. The challenge with conventional computers is that the key size for RSA today is 2048 or 4096 bits, so you are looking at O(2^2048) size search spaces, which is unsearchable in anyone's lifetime (and the reason no one is breaking the RSA keys directly). One of the foundational algorithms for quantum computers is Shore's algorithm (en.wikipedia.org/wiki/Shor%27s_algorithm), which in the best case can factor large numbers O(log 2^2048) which is roughly O(~600), a much more achievable complexity! Today's quantum computers are still too immature to factor large numbers, but as the technology improves, there may someday come a time when a quantum computer can brute force discover an RSA private key, which would be pure chaos for the internet because anyone with a quantum computer could pose as anyone else on the internet (and create their digital signatures, etc...), so cryptographers are busy at work today to develop asymmetric key ciphers that utilize one-way functions that are not amenable to any known quantum algorithms.
@joelmandebi7212 Жыл бұрын
Very insightful discussion. Thanks Prof Austin.
@steen1video Жыл бұрын
Excellent points! I encountered many of them in my PhD journey😀
@leoudeji Жыл бұрын
Thanks alot Prof. Austin for taking the time to share these tips.
@schoolofthought. Жыл бұрын
Professor Thanks a lot for sharing
@Hayat-bk3bv2 жыл бұрын
Thanks so much for sharing . I'm actually "Faking it till I make it" and I believe I will make it :)
@samuelwozab25002 жыл бұрын
Hello , How can I apply for AURA 2023 research program? am currently 4th year undergraduate mechanical engineering student at Addis Ababa institute of Technology. please contact me at my email address: [email protected]
@MohamedIbrahim-nq4oh2 жыл бұрын
Prof. Austin: Thanks a lot for sharing this great video!
@moloned3 жыл бұрын
Sounds like a great tool especially when combined with edge AI and compute
@Basil-the-Frog3 жыл бұрын
Valgrind is pronounced val-grinned.
@GeorgWilde3 жыл бұрын
"Morpheus attack deterctors discern normal code from malicious code, via undefiend semantics" - So you have solved halting problem? :-D
@mehdis.74043 жыл бұрын
very insightful, thanks Todd for sharing! coarse grained reconfigurable architecture comes to my mind that can be customized for different tasks
@leonardotoshinobukimura29553 жыл бұрын
it is amazing!!
@jamesclarity10773 жыл бұрын
Great project
@jamesclarity10773 жыл бұрын
"No one has broken AES". Quantum computing. Hold my beer
@Jasruler3 жыл бұрын
AES-256 is not going to be broken by a quantum computer for a very long time.