1. What contributions have the authors mentioned in the paper "A formal framework for program anomaly detection" ?
In this paper, the authors formalize the general program anomaly detection problem and point out two of its key properties.. The authors present a unified framework to present any program anomaly detection method in terms of its detection capability.. The authors prove the theoretical accuracy limit for program anomaly detection with an abstract detection machine.. The authors show how existing solutions are positioned in their framework and illustrate the gap between state-of-the-art methods and the theoretical accuracy limit.. The authors also point out some potential modeling features for future program anomaly detection evolution.
read more
2. What have the authors stated for future works in "A formal framework for program anomaly detection" ?
More accurate context-sensitive language models can be explored with pragmatic constraints in the future.. Their framework has the potential to serve as a roadmap and help researchers approach the ultimate program defense without attack signature specification.
read more
3. What are the main types of control-flow enforcement techniques?
Control-flow enforcement techniques range from the protection of return addresses, the protection of indirect control-flow transfers (CFI), to the protection of all code pointers (CPI).
read more
4. What are the common probabilistic detection methods?
Typical probabilistic detection methods include hidden Markov model (HMM) [61, 64], classification methods [16, 37, 41, 46], artificial neural network [27], data mining approaches [40], etc.
read more
