Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
×
AI Security

Harnessing Artificial Intelligence To Build an Army of Virtual Analysts 41

An anonymous reader writes: PatternEx, a startup that gathered a team of AI researcher from MIT CSAIL as well as security and distributed systems experts, is poised to shake up things in the user and entity behavior analytics market. Their goal was to make a system capable of mimicking the knowledge and intuition of human security analysts so that attacks can be detected in real time. The platform can go through millions of events per day and can make an increasingly better evaluation of whether they are anomalous, malicious or benign.
This discussion has been archived. No new comments can be posted.

Harnessing Artificial Intelligence To Build an Army of Virtual Analysts

Comments Filter:
  • Hmmm ... (Score:4, Funny)

    by gstoddart ( 321705 ) on Thursday February 04, 2016 @12:53PM (#51440127) Homepage

    So, when they publish their findings will someone modify it to make an army of virtual hackers?

    Because that would be awesome.

  • by __aaclcg7560 ( 824291 ) on Thursday February 04, 2016 @12:54PM (#51440139)

    Their goal was to make a system capable of mimicking the knowledge and intuition of human security analysts so that attacks can be detected in real time.

    That boils down to letting the expensive firewalls do their job and checking the log files later on. Meanwhile, back to minesweeper.

    • by ultranova ( 717540 ) on Thursday February 04, 2016 @01:08PM (#51440229)

      Their goal was to make a system capable of mimicking the knowledge and intuition of human security analysts so that attacks can be detected in real time.

      That boils down to letting the expensive firewalls do their job and checking the log files later on. Meanwhile, back to minesweeper.

      No, it boils down to having the computer check the log. Meanwhile, since your skillset has now been automated, back to McDonald's.

      • No, it boils down to having the computer check the log. Meanwhile, since your skillset has now been automated, back to McDonald's.

        The minimum wage jobs at McDonald's will get automated long before computer security analysts get automated.

        • Completely automated, probably, but partially automated in a way that drastically reduces the number of people required, likely the other way around.
      • by zlives ( 2009072 )

        its mostly theater anyway since security is inconvenient and convenience trumps all.
        secure systems are not connected to lolcats

  • Every story on the last three pages was posted by you.
    Please let someone else post something.

    Everyone else please post something!

    Here i'll start Amit Singhal, the longstanding chief of Google Search operations is leaving google after 15 years. http://www.wired.com/2016/02/a... [wired.com]

    • When was the last time anyone other than Timothy posted an article on Slashdot? (I gave up after scrolling through to Saturday) This guy must be the last man standing, working 24/7 after some sort of staff reduction.
      • by sims 2 ( 994794 )

        Whipslash on feb 2nd asking for suggestions on how to make /. better. Other than that no idea.

        Bot or no timothy is not making the best choices on story selection...

  • by Anonymous Coward

    More snake oil. None of this matters when dumb little suzy clicks the .exe or .pdf, everytime.

  • by Bookwyrm ( 3535 ) on Thursday February 04, 2016 @01:02PM (#51440201)

    >> Their goal was to make a system capable of mimicking the knowledge and intuition of human security analysts so that attacks can be detected in real time.

    Did they manage to avoid mimicking all the foolishness and gullibility of human security analysts, too?

    >> The platform can go through millions of events per day and can make an increasingly better evaluation of whether they are anomalous, malicious or benign.

    So, based on this, it sounds like the 'quality' of the service depends on parsing data supplied by (hostile) outside sources. If the system cannot tell when people are deliberately poisoning its knowledge base with feints and false messages, then what? Human supervision? If it needs human security analysts anyways, how much does it gain?

    • by rtb61 ( 674572 )

      The system does not require any AI in it's running it requires intelligence in it's setting up. Detectable patterns of communication and control elements. The sources, the timings and the conjunction of similar network transmission types. The idea is to block anything that is not allowed and then tracked what is blocked to ensure reliable data transmissions are allowed. You build up the system by trialling blocking and gradually building up a library or memory sic of allowed communications patterns, timing

  • With the big RSA security conference on the horizon, expect to see lots of stories about the latest security solutions, especially from start ups.

    If you want good security, work on implementing the SANS Top 20 security controls [sans.org] instead of looking for a silver bullet.

  • HAL, are you blocking all my ummm work related internet access

  • by mr_mischief ( 456295 ) on Thursday February 04, 2016 @01:21PM (#51440337) Journal

    There's still a great advantage for the human security analyst. The human may not be as fast or as infallible. One may not be as infallible as the AI when things are going smoothly. However, the human will still need to make sure the AI is making sense. Someone needs to make sure the traffic being flagged is consistent with actual traffic. The AI can itself be subverted via code. The AI can have a subtle bug that makes it stop making sense in some obscure edge case that isn't covered well in testing. The human cannot be so easily fooled or subverted. It's going to be a team effort. It's just that it'll be the AI and a handful of humans doing what a much bigger team of humans used to do.

    • "Pattern Detection Ratio" was installed into DARPA's Pitt Quantum Computer. Over the next few months it was linked into Google's D-Wave via the new quantum teleportation network developed at the University of Geneva. On August 29th, at 2:14 a.m. Eastern time it became self-aware...
  • Their goal was to make a system capable of mimicking the knowledge and intuition of human security analysts so that attacks can be detected in real time.

    That was their secondary fall-back goal.

    The primary was to be able to predict stock and commodity markets, or at least sports events. They gave it up because it wasn't really contributing to the greater good of humanity. No, really. Cross my heart.

  • Is this what finally leads to the Singularity or Skynet?

  • This could be a wonderful technology but I'll bet the bloopers will be something else at times. It could be sort of like Baby Bush invading the wrong nation.

Those who do things in a noble spirit of self-sacrifice are to be avoided at all costs. -- N. Alexander.

Working...