Security Researchers Detail New "BlindSide" Speculative Execution Attack

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts
  • onlyLinuxLuvUBack
    Senior Member
    • May 2019
    • 666

    #11
    The next intel "Emmental cheese"-lake should probably just use the Intel 14nm++++++++++++++++++++++++++++++++++++++++++++(c )(tm) manufacturing process and just place isolated "thoroughly" scrubbed "secure" cpu pentium 3 cores and throw in a fpga cpu core in case things like this happen.

    Last edited by onlyLinuxLuvUBack; 11 September 2020, 05:10 PM. Reason: swiss-lake may not be worldwide understoood

    Comment

    • tildearrow
      Senior Member
      • Nov 2016
      • 7097

      #12
      Root exploit?

      Let's just kill computing, if we found the absolute vulnerability...

      Comment

      • starshipeleven
        Premium Supporter
        • Dec 2015
        • 14568

        #13
        Originally posted by Raka555 View Post
        Can we get a 5Ghz Cortex-A53, please...
        Are ARM immune or did they just not test them? Because they do speculative execution too

        Comment

        • starshipeleven
          Premium Supporter
          • Dec 2015
          • 14568

          #14
          Originally posted by Spam View Post
          Is this attack even plausible? Seems it is dependent on other faults first?
          It needs a memory corruption bug to happen, and since linux kernel is written in C this isn't uncommon.
          But once that happens with this trick you can bypass kernel address randomization and get through, while without this bug the kernel randomization would stop you from abusing a memory corruption bug.

          Comment

          • starshipeleven
            Premium Supporter
            • Dec 2015
            • 14568

            #15
            Originally posted by tildearrow View Post
            Root exploit?

            Let's just kill computing, if we found the absolute vulnerability...
            yeah it's kind of weird to use a kernel-level exploit to leak the root password, but that's probably the easiest thing they could do to show that they can read whatever the fuck they want from system RAM, and that nothing is safe.

            They are literally just reading the hash from the / etc / passwd file after they have loaded in disk cache (i.e. RAM) by trying a sudo login.

            Comment

            • starshipeleven
              Premium Supporter
              • Dec 2015
              • 14568

              #16
              Originally posted by onlyLinuxLuvUBack View Post
              The next intel swiss-lake should probably just use the Intel 14nm++++++++++++++++++++++++++++++++++++++++++++(c )(tm) manufacturing process and just place isolated "thoroughly" scrubbed "secure" cpu pentium 3 cores and throw in a fpga cpu core in case things like this happen.
              Yo dawg I heard you like security so we added a secure CPU in your secure CPU so you can be secure while you are secure

              Comment

              • CochainComplex
                Senior Member
                • May 2016
                • 2257

                #17
                so where are the non speculative CPU's? is it still possible or will this push us back to pre-P4 era (performancewise)?

                Comment

                • brauliobo
                  Junior Member
                  • Sep 2015
                  • 28

                  #18
                  Amazing got root in the end of the video

                  Comment

                  • Amaranth
                    Phoronix Member
                    • Apr 2008
                    • 54

                    #19
                    Originally posted by CochainComplex View Post
                    so where are the non speculative CPU's? is it still possible or will this push us back to pre-P4 era (performancewise)?
                    I don't know what the performance would look like with modern processes and clocks but architecturally this would be back to something more like the original Pentium or the early Atom designs.

                    Comment

                    • bison
                      Senior Member
                      • Oct 2013
                      • 218

                      #20
                      Originally posted by Raka555 View Post
                      Can we get a 5Ghz Cortex-A53, please...
                      That would be excellent.

                      I wonder how many more years it will be until the realization comes: "We need to give up on OoO execution."

                      Comment

                      Working...
                      X