ABSTRACT
We present an approach for detecting sensor spoo fing
attacks on a cyber-physical system. Our approach consists of
two steps. In the fi rst step, we construct a safety envelope of
the system. Under nominal conditions (that is, when there
are no attacks), the system always stays inside its safety envelope.
In the second step, we build an attack detector monitor
that executes synchronously with the system and raises
an alarm whenever the system state falls outside the safety
envelope. We synthesize safety envelopes using a modified
machine learning procedure applied on data collected from
the system when it is not under attack. We present experimental
results that show e ffectiveness of our approach, and
also validate the several novel features that we introduced
We present an approach for detecting sensor spoo fing
attacks on a cyber-physical system. Our approach consists of
two steps. In the fi rst step, we construct a safety envelope of
the system. Under nominal conditions (that is, when there
are no attacks), the system always stays inside its safety envelope.
In the second step, we build an attack detector monitor
that executes synchronously with the system and raises
an alarm whenever the system state falls outside the safety
envelope. We synthesize safety envelopes using a modified
machine learning procedure applied on data collected from
the system when it is not under attack. We present experimental
results that show e ffectiveness of our approach, and
also validate the several novel features that we introduced
in our learning procedure
more here..........http://www.csl.sri.com/users/tiwari/papers/hicons14.pdf