This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Connectionist Password Quality Tester
July/August 2002 (vol. 14 no. 4)
pp. 920-922

We present a simple connectionist algorithm for testing the quality of computer passwords. Password quality is evaluated by testing the string against a large dictionary of words stored in a network in distributed form. Numerical simulations demonstrate the effectiveness of this approach. Computer security has always been an issue, more so in recent years due to the global network access. In this correspondence, we present a simple connectionist algorithm for testing the quality of computer passwords. A popular method of evaluating password quality is to test it against a large dictionary of words and near-words. Our algorithm is an approximate realization of this method. The large dictionary of words is stored in the network in distributed form. All stored words are stable; however, spurious memories may develop. Although there is no easy way to determine exactly which nonword strings become spurious, nor even exactly how many spurious memories form, the numerical simulations below reveal that the network works well in distinguishing words and near-words from structure-less strings. Thus, to evaluate a password, one would present it to the network and, if the network labeled it a memory, the password would be considered bad, otherwise good.

[1] J. Hertz, A. Krogh, and R.G. Palmer, Introduction to the Theory of Neural Computation. Addison-Wesley, 1991.
[2] J.J. Hopfield, “Neural Networks and Physical Systems with Emergent Collective Computational Abilities,” Proc. Nat'l Academy of Sciences, vol. 79, 1982.
[3] A. Jagota, “Applying a Hopfield-Style Network to Degraded Text Recognition,” Proc. Int'l Joint Conf. Neural Networks, vol. 1, pp. 27–32, 1990.
[4] A. Jagota, “Novelty Detection on a Very Large Number of Memories Stored in a Hopfield-Style Network,” Proc. Int'l Joint Conf. Neural Networks, 1991.
[5] A. Jagota, “Contextual Word Recognition with a Hopfield-Style Net,” Neural, Parallel,&Scientific Computations, vol. 2, no. 2, pp. 245–271, 1994.
[6] A. Jagota, G. Narasimhan, and K.W. Regan, “Information Capacity of Binary Weights Associative Memories,” Neurocomputing, 1998.
[7] M. Misra, “Parallel Environments for Implementing Neural Networks,” Neural Computing Surveys, vol. 1, no. 2, pp. 1–17, 1998, e-version athttp://www.cs.auc.dk/general/DBS/tdb/TimeCenter/ publications2.htmlhttp://www.icsi.berkeley.edu/ jagotaNCS.
[8] E.M. Riseman and R.W. Ehrich, “Contextual Word Recognition Using Binary Digrams,” IEEE Trans. Computers, vol. 20, no. 4, pp. 397–403, Apr. 1971.
[9] I. Shariv, T. Grossman, E. Domany, and A.A. Friesem, “All-Optical Implementation of the Inverted Neural Network Model,” Optics in Complex Systems, vol. 1319, 1990.

Index Terms:
Hopfield networks, edit distance, string searching, spurious memories.
Citation:
Nigel Duffy, Arun Jagota, "Connectionist Password Quality Tester," IEEE Transactions on Knowledge and Data Engineering, vol. 14, no. 4, pp. 920-922, July-Aug. 2002, doi:10.1109/TKDE.2002.1019222
Usage of this product signifies your acceptance of the Terms of Use.