Malicious activity probability determinations for autonomous systems
According to examples, an apparatus may include a processor that may calculate a normalized threat intelligence score (TIS) for an autonomous system (AS) based on a sum of threat intelligence (TI) signals associated with Internet protocol (IP) addresses controlled by the AS and a count of the IP addresses controlled by the AS. The processor may also determine, based on the normalized TIS for the AS, a probability that activities associated with the IP addresses controlled by the AS are likely to be malicious. The processor may further output the determined probability that the activities associated with the IP addresses controlled by the AS are likely to be malicious.
1. An apparatus comprising:
a processor; and
a memory on which is stored machine-readable instructions that when executed by the processor, cause the processor to:
determine a count of Internet Protocol (IP) addresses controlled by an autonomous system (AS);
generate threat intelligence (TI) signals for a subset of the IP addresses controlled by the AS based on detected malicious activity;
calculate a normalized threat intelligence score (TIS) for the AS based on a sum of the TI signals associated with the IP addresses controlled by the AS and the determined count of the IP addresses controlled by the AS;
determine, based on the normalized TIS for the AS, a probability that activities associated with the IP addresses controlled by the AS are likely to be malicious; and
output the determined probability that the activities associated with the IP addresses controlled by the AS are likely to be malicious.
2. The apparatus of claim 1 , wherein the instructions cause the processor to:
calculate the normalized TIS for the AS using a logistic transformation of the sum of TI signals associated with the IP addresses controlled by the AS and the determined count of the IP addresses controlled by the AS.
3. The apparatus of claim 1 , wherein the instructions cause the processor to:
calculate the normalized TIS for the AS using a logistic transformation of a weighted sum of TI signals associated with the IP addresses controlled by the AS and the determined count of the IP addresses controlled by the AS.
4. The apparatus of claim 3 , wherein the instructions cause the processor to:
apply different levels of weights to the TI signals dependent upon types of the TI signals; and
determine the weighted sum of TI signals based on the levels of weights applied to the TI signals.
5. The apparatus of claim 1 , wherein the instructions cause the processor to:
apply a scaling parameter to the determined count of the IP addresses controlled by the AS, wherein the scaling parameter controls an impact of the count of the IP addresses on the TIS.
6. The apparatus of claim 5 , wherein the instructions cause the processor to:
apply a certain scaling parameter to the count of the IP addresses based on a geographic location of the AS.
7. The apparatus of claim 1 , wherein the instructions cause the processor to:
calculate normalized TIS's for a plurality of AS's;
determine, based on the normalized TIS's for the plurality of AS's and for each of the plurality of AS's, a probability that activities associated with IP addresses controlled by the AS are likely to be malicious; and
output the determined probabilities of the activities associated with the IP addresses controlled by the AS's are likely to be malicious.
8. The apparatus of claim 7 , wherein the instructions cause the processor to:
generate a histogram of the AS's according to the normalized TIS's for the plurality of AS's;
determine groups of the plurality of AS's from the histogram; and
assign reputation levels to each of the plurality of AS's according to the groups in which the plurality of AS's are determined to belong.
9. The apparatus of claim 1 , wherein the instructions cause the processor to:
determine whether the determined probability that the activities associated with the IP addresses controlled by the AS are likely to be malicious exceeds a predefined threshold level; and
output the determined probability based on the determined probability exceeding the predefined threshold level.
10. A method comprising:
accessing, by a processor, a count of Internet Protocol (IP) addresses controlled by an autonomous system (AS);
generating, by a processor, threat intelligence (TI) signals for a subset of IP addresses controlled by the AS based on detected malicious activity;
accessing, by a processor, information regarding the AS, the information including the TI signals associated with the IP addresses controlled by the AS and a count of the IP addresses controlled by the AS;
calculating, by the processor, a normalized threat intelligence score (TIS) for the AS based on a weighted sum of the TI signals and the count of the IP addresses controlled by the AS;
determining, by the processor, a reputation level of the AS based on the normalized TIS for the AS; and
outputting, by the processor, the determined reputation level of the AS.
11. The method of claim 10 , further comprising:
determining whether the determined reputation level falls below a predefined reputation threshold level; and
outputting the determined reputation level of the AS in response to a determination that the determined reputation level falls below the predefined reputation threshold level.
12. The method of claim 10 , further comprising:
calculating the normalized TIS for the AS using a logistic transformation of the weighted sum of TI signals associated with the IP addresses controlled by the AS and the count of the IP addresses controlled by the AS.
13. The method of claim 12 , further comprising:
applying different levels of weights to the TI signals depending upon the types of the TI signals; and
determine the weighted sum of TI signals based on the levels of weights applied to the TI signals.
14. The method of claim 12 , further comprising:
applying a scaling parameter to the count of the IP addresses controlled by the AS, wherein the scaling parameter controls an impact of the count of the IP addresses on the TIS.
15. The method of claim 10 , further comprising:
accessing information regarding a plurality of AS's, the information including TI signals associated with IP addresses controlled by the plurality of AS's and counts of the IP addresses controlled by the plurality of AS's;
calculating normalized TIS's for the plurality of AS's;
determining, based on the normalized TIS's for the plurality of AS's and for each of the plurality of AS's, a reputation level of the AS; and
outputting the determined reputation levels of the AS's.
16. The method of claim 15 , further comprising:
generating a histogram of the AS's according to the normalized TIS's for the plurality of AS's;
determining groups of the plurality of AS's from the histogram; and
assigning reputation levels to each of the plurality of AS's according to the groups in which the plurality of AS's are determined to belong.
17. A non-transitory computer-readable medium on which is stored a plurality of instructions that when executed by a processor, cause the processor to:
access a count of Internet Protocol (IP) addresses controlled by an autonomous system (AS);
generate threat intelligence (TI) signals for a subset of the IP addresses controlled by the AS based on detected malicious activity;
access information regarding the AS, the information including the TI signals associated with the IP addresses controlled by the AS and a count of the IP addresses controlled by the AS;
calculate a normalized threat intelligence score (TIS) for the AS based on a weighted sum of the TI signals and the count of the IP addresses controlled by the AS;
determine a reputation level of the AS based on the normalized TIS for the AS; and
output the determined reputation level of the AS.
18. The computer-readable medium of claim 17 , wherein the instructions cause the processor to:
determine whether the determined reputation level falls below a predefined reputation threshold level; and
output the determined reputation level of the AS in response to a determination that the determined reputation level falls below the predefined reputation threshold level.
19. The computer-readable medium of claim 17 , wherein the instructions cause the processor to:
apply different levels of weights to the TI signals depending upon the types of the TI signals;
determine the weighted sum of TI signals based on the levels of weights applied to the TI signals; and
calculate the normalized TIS for the AS using a logistic transformation of the weighted sum of TI signals associated with the IP addresses controlled by the AS and the count of the IP addresses controlled by the AS.
20. The computer-readable medium of claim 17 , wherein the instructions cause the processor to:
apply a scaling parameter to the count of the IP addresses controlled by the AS, wherein the scaling parameter controls an impact of the count of the IP addresses on the TIS.