Artificial Immune Systems: An Emerging Technology

1
Artificial Immune Systems An Emerging Technology
Congress on Evolutionary Computation 2001.
Seoul, Korea.

• Dr. Jonathan Timmis
• Computing Laboratory
• University of Kent at Canterbury
• England. UK.
• J.Timmis_at_ukc.ac.uk
• http/www.cs.ukc.ac.uk/people/staff/jt6

2
Tutorial Overview

• What are Artificial Immune Systems?
• Background immunology
• Why use the immune system as a metaphor
• Immune Metaphors employed
• Review of AIS work
• Applications
• More blue sky research

3
Immune metaphors
Other areas
Idea!
Idea
Artificial Immune Systems
Immune System
4
Artificial Immune Systems

• Relatively new branch of computer science
• Some history
• Using natural immune system as a metaphor for
  solving computational problems
• Not modelling the immune system
• Variety of applications so far
• Fault diagnosis (Ishida)
• Computer security (Forrest, Kim)
• Novelty detection (Dasgupta)
• Robot behaviour (Lee)
• Machine learning (Hunt, Timmis, de Castro)

5
Why the Immune System?

• Recognition
• Anomaly detection
• Noise tolerance
• Robustness
• Feature extraction
• Diversity
• Reinforcement learning
• Memory
• Distributed
• Multi-layered
• Adaptive

6
Part I Basic Immunology
7
Role of the Immune System

• Protect our bodies from infection
• Primary immune response
• Launch a response to invading pathogens
• Secondary immune response
• Remember past encounters
• Faster response the second time around

8
How does it work?
9
Where is it?
10
Multiple layers of the immune system
11
Immune Pattern Recognition

• The immune recognition is based on the
  complementarity between the binding region of the
  receptor and a portion of the antigen called
  epitope.
• Antibodies present a single type of receptor,
  antigens might present several epitopes.
• This means that different antibodies can
  recognize a single antigen

12
Antibodies
Antibody Molecule
Antibody Production
13
Clonal Selection
14
T-cells

• Regulation of other cells
• Active in the immune response
• Helper T-cells
• Killer T-cells

15
Main Properties of Clonal Selection (Burnet, 1978)

• Elimination of self antigens
• Proliferation and differentiation on contact of
  mature lymphocytes with antigen
• Restriction of one pattern to one differentiated
  cell and retention of that pattern by clonal
  descendants
• Generation of new random genetic changes,
  subsequently expressed as diverse antibody
  patterns by a form of accelerated somatic
  mutation

16
Reinforcement Learning and Immune Memory

• Repeated exposure to an antigen throughout a
  lifetime
• Primary, secondary immune responses
• Remembers encounters
• No need to start from scratch
• Memory cells
• Associative memory

17
Learning (2)
18
Immune Network Theory

• Idiotypic network (Jerne, 1974)
• B cells co-stimulate each other
• Treat each other a bit like antigens
• Creates an immunological memory

19
Immune Network Theory(2)
20
Shape Space Formalism

• Repertoire of the immune system is complete
  (Perelson, 1989)
• Extensive regions of complementarity
• Some threshold of recognition

V

V
e
e
V
e
e




V
e
e


21
Self/Non-Self Recognition

• Immune system needs to be able to differentiate
  between self and non-self cells
• Antigenic encounters may result in cell death,
  therefore
• Some kind of positive selection
• Some element of negative selection

22
Summary so far .

• Immune system has some remarkable properties
• Pattern recognition
• Learning
• Memory
• So, is it useful?

23
Some questions for you !
24
Part II A Review of Artificial Immune Systems
25
Topics to Cover

• A few disclaimers
• I can not cover everything as there is a large
  amount of work out there
• To do so, would be silly ?
• Proposed general frameworks
• Give an overview of significant application areas
  and work therein
• I am not an expert in all the problem domains
• I would earn more money if I was !

26
Shape Space

• Describe interactions between molecules
• Degree of binding between molecules
• Complement threshold
• Each paratope matches a certain region of space
• Complete repertoire

27
Representation and Affinities

• Representation affects affinity measure
• Binary
• Integer
• Affinity is related to distance
• Euclidian
• Hamming
• Affinity threshold

28
Basic Immune Models and Algorithms

• Bone Marrow Models
• Negative Selection Algorithms
• Clonal Selection Algorithm
• Somatic Hypermutation
• Immune Network Models

29
Bone Marrow Models

• Gene libraries are used to create antibodies from
  the bone marrow
• Antibody production through a random
  concatenation from gene libraries
• Simple or complex libraries

30
Negative Selection Algorithms

• Forrest 1994 Idea taken from the negative
  selection of T-cells in the thymus
• Applied initially to computer security
• Split into two parts
• Censoring
• Monitoring

31
Negative Selection Algorithm

• Each copy of the algorithm is unique, so that
  each protected location is provided with a unique
  set of detectors
• Detection is probabilistic, as a consequence of
  using different sets of detectors to protect each
  entity
• A robust system should detect any foreign
  activity rather than looking for specific known
  patterns of intrusion.
• No prior knowledge of anomaly (non-self) is
  required
• The size of the detector set does not necessarily
  increase with the number of strings being
  protected
• The detection probability increases exponentially
  with the number of independent detection
  algorithms
• There is an exponential cost to generate
  detectors with relation to the number of strings
  being protected (self).
• Solution to the above in Dhaeseleer et al.
  (1996)

32
Somatic Hypermutation

• Mutation rate in proportion to affinity
• Very controlled mutation in the natural immune
  system
• Trade-off between the normalized antibody
  affinity D and its mutation rate ?,

33
Immune Network Models

• Timmis Neal, 2000
• Used immune network theory as a basis, proposed
  the AINE algorithm

Initialize AIN For each antigen Present antigen
to each ARB in the AIN Calculate ARB stimulation
level Allocate B cells to ARBs, based on
stimulation level Remove weakest ARBs (ones that
do not hold any B cells) If termination condition
met exit else Clone and mutate remaining
ARBs Integrate new ARBs into AIN
34
Immune Network Models

• De Castro Von Zuben (2000c)
• aiNET, based in similar principles

At each iteration step do For each antigen
do Determine affinity to all network
cells Select n highest affinity network
cells Clone these n selected cells Increase the
affinity of the cells to antigen by reducing the
distance between them (greedy search) Calculate
improved affinity of these n cells Re-select a
number of improved cells and place into matrix
M Remove cells from M whose affinity is below a
set threshold Calculate cell-cell affinity
within the network Remove cells from network
whose affinity is below a certain
threshold Concatenate original network and M to
form new network Determine whole network
inter-cell affinities and remove all those below
the set threshold Replace r of worst
individuals by novel randomly generated ones Test
stopping criterion
35
Part III - Applications
36
Anomaly Detection

• The normal behavior of a system is often
  characterized by a series of observations over
  time.
• The problem of detecting novelties, or anomalies,
  can be viewed as finding deviations of a
  characteristic property in the system.
• For computer scientists, the identification of
  computational viruses and network intrusions is
  considered one of the most important anomaly
  detection tasks

37
Virus Detection

• Protect the computer from unwanted viruses
• Initial work by Kephart 1994
• More of a computer immune system

38
Virus Detection (2)

• Okamoto Ishida (1999a,b) proposed a distributed
  approach
• Detected viruses by matching self-information
• first few bytes of the head of a file
• the file size and path, etc.
• against the current host files.
• Viruses were neutralized by overwriting the
  self-information on the infected files
• Recovering was attained by copying the same file
  from other uninfected hosts through the computer
  network

39
Virus Detection (3)

• Other key works include
• A distributed self adaptive architecture for a
  computer virus immune system (Lamont, 200)
• Use a set of co-operating agents to detect
  non-self patterns

40
Security

• Somayaji et al. (1997) outlined mappings between
  IS and computer systems
• A security systems need
• Confidentiality
• Integrity
• Availability
• Accountability
• Correctness

41
IS to Security Systems
42
Network Security

• Hofmeyr Forrest (1999, 2000) developing an
  artificial immune system that is distributed,
  robust, dynamic, diverse and adaptive, with
  applications to computer network security.
• Kim Bentley (1999). New paper here at CEC so I
  wont cover it, go see it for yourself!

43
Forrests Model
External
host
Randomly
created
Host

ip 20.20.15.7
010011100010.....001101
Activation

port 22
Detector
threshold
set
Immature
Datapath
triple
Cytokine
level
No
match
during
(20.20.15.7, 31.14.22.87,
Internal
tolerization
ftp)
host
Permutation
mask
Exceed
Mature
Naive
activation
ip 31.14.22.87
threshold
Match
port 2000
Dont
during
Match
exceed
tolerization
Detector
Activated
activation
threshold
0100111010101000110......101010010
No
Co stimulation
co stimulation
memory

immature
activated
matches
Death
Memory
Broadcast LAN
  AIS for computer network security. (a)
Architecture. (b) Life cycle of a detector.
44
Novelty Detection

• Image Segmentation McCoy Devarajan (1997)
• Detecting road contours in aerial images
• Used a negative selection algorithm

45
Hardware Fault Tolerance
Table 4.1.           

• Immunotronics (Bradley Tyrell, 2000)
• Use negative selection algorithm for fault
  tolerance in hardware

 
46
Machine Learning

• Early work on DNA Recognition
• Cooke and Hunt, 1995
• Use immune network theory
• Evolve a structure to use for prediction of DNA
  sequences
• 90 classification rate
• Quite good at the time, but needed more
  corroboration of results

47
Unsupervised Learning

• Timmis, 2000
• Based on Hunts work
• Complete redesign of algorithm AINE
• Immune metadynamics
• Shape space
• Few initial parameters
• Stabilises to find a core pattern within a
  network of B cells

48
Results (Timmis, 2000)
49
Another approach

• de Castro and von Zuben, 2000
• aiNET cf. SOFM
• Use similar ideas to Timmis
• Immune network theory
• Shape space
• Suppression mechanism different
• Eliminate self similar cells under a set
  threshold
• Clone based on antigen match, network not taken
  into account

50
Results (de Castro von Zuben, 2001)
Test Problem
Result from aiNET
51
Supervised Approach

• Carter, 2000
• Pattern recognition and classification system
  Immunos-81
• Use T-cells, B-cells, antibodies and amino-acid
  library
• Builds a library of data types and classes
• System can generalise
• Good classification rates on sample data sets

52
Robotics

• Behaviour Arbitration
• Ishiguro et al. (1996, 1997) Immune network
  theory to evolve a behaviour among a set of
  agents
• Collective Behaviour
• Emerging collective behaviour through
  communicating robots (Jun et al, 1999)
• Immune network theory to suppress or encourage
  robots behaviour

53
Scheduling

• Hart et al. (1998) and Hart Ross (1999a)
• Proposed an AIS to produce robust schedules
• for a dynamic job-shop scheduling problem in
  which jobs arrive continually, and the
  environment is subject to changes.
• Investigated is an AIS could be evolved using a
  GA approach
• then be used to produce sets of schedules which
  together cover a range of contingencies,
  predictable and unpredictable.
• Model included evolution through gene libraries,
  affinity maturation of the immune response and
  the clonal selection principle.

54
Diagnosis

• Ishida (1993)
• Immune network model applied to the process
  diagnosis problem
• Later was elaborated as a sensor network that
  could diagnose sensor faults by evaluating
  reliability of data from sensors, and process
  faults by evaluating reliability of constraints
  among data.
• Main immune features employed
• Recognition is performed by distributed agents
  which dynamically interact with each other
• Each agent reacts based solely on its own
  knowledge and
• Memory is realized as stable equilibrium points
  of the dynamical network.

55
Summary

• Covered much, but there is much work not covered
  (so apologies to anyone for missing theirs)
• Immunology
• Immune metaphors
• Antibodies and their interactions
• Immune learning and memory
• Self/non-self
• Negative selection
• Application of immune metaphors

56
The Future

• Rapidly growing field that I think is very
  exciting
• Much work is very diverse
• Need of a general framework
• Wide possible application domains
• Lots of work to do . Keep me in a job for quite
  a while yet ?