Re: [logs] AI/adaptive/heuristic syslog analysis

From: Jon Stearley (jrstearat_private)
Date: Fri Dec 21 2001 - 10:44:44 PST

  • Next message: Bennet S. Yee: "Re: [logs] AI/adaptive/heuristic syslog analysis"

    On Fri, Dec 21, 2001 at 02:25:15AM -0800, dgillettat_private wrote:
    >   I have three basic concerns with this approach:
    > 
    > 1.  A stealthy/patient attacker might be able to stay "below radar" 
    > while the system acclimates to his presence.  i.e. Normal/routine may 
    > not equate to *authorized*.
    > 
    > 2.  Anent the recent thread about court admissability, it is likely 
    > to become necessary to explain why such a system flagged some 
    > particular traffic.  I haven't followed the field closely, but my 
    > impression has long been that reporting/reproducing the learned 
    > "reasoning" is a particularly thorny issue.
    > 
    > 3.  There remain persistent anecdotes to the effect that some 
    > automated British defence system, during the 1982 Falklands war, 
    > detected an incoming missile, identified it as an Exocet, and on that 
    > basis classified it as "friendly" -- even though it was rapidly 
    > closing on a British ship.  I think there has to remain some human 
    > interface to the ruleset, so that for instance an administrator can 
    > revoke permissions previously granted to some traffic.  I'm not sure 
    > how else to get such a learning system to converge on policy changes 
    > in an acceptable time.
    
    three excellent points!  i agree absolutely.  definately, i see the ai
    thing as a researchy approach rather than something i'd currently
    employ to protect/defend anything valuable.  it's a fun thing (for me
    anyway), but with significant potential i think.
    
    here's two "computer immunology" links which are not directly related
    to loganalysis, but are indirectly/philosophically in the current
    context:
       http://www.cs.unm.edu/~immsec/
       http://www.iu.hio.no/~mark/research/immunology.html
    
    my limited understanding of biological immune systems is that they are
    much more effective at protecting a species than individuals.  this
    has bad/unacceptable implications for the current client/server
    computing model - especially because the servers are so easy to
    identify!  but, as computing becomes more and more distributed, who
    knows...
    
    --
    +--------------------------------------------------------------+
    | Jon Stearley			(505) 845-7571  (FAX 844-2067) |
    | Compaq Federal LLC		High Performance Solutions     |
    | Sandia National Laboratories	Scalable Systems Integration   |
    +--------------------------------------------------------------+
    
    
    ---------------------------------------------------------------------
    To unsubscribe, e-mail: loganalysis-unsubscribeat_private
    For additional commands, e-mail: loganalysis-helpat_private
    



    This archive was generated by hypermail 2b30 : Fri Dec 21 2001 - 11:19:11 PST