Hacker News new | ask | show | jobs
Show HN: Intrusion Detection in Real-time (arxiv.org)
69 points by siddhartb_ 2251 days ago
6 comments
siddhartb_ 2251 days ago
Code is available in C++, Python, Ruby, R, and Rust at https://github.com/bhatiasiddharth/MIDAS
link
janesconference 2250 days ago
Really cool project. I'm doing a real-time version (gets input on stdin, sends output on stdout), will probably release the code soon.
link
shivin9 2251 days ago
Can this detect DDoS like attacks also?
link
siddhartb_ 2251 days ago
We handle locality in terms of both source and destination, therefore we should be able to handle both DoS and DDoS attacks.
link
NimishMishra 2251 days ago
Looks interesting. Better than some of the static detection algorithms out there
link
GurbakshSharma 2251 days ago
can you list out use cases where we can use this algorithm?
link
siddhartb_ 2251 days ago
In addition to detecting intrusions, it can detect fake ratings and frauds. Basically finding anomalous and suspicious behavior in any dynamic (time-evolving) graph.
link
udaychopra 2251 days ago
Hi, how will the performance be affected if let's say time ticks are not uniform?
link
siddhartb_ 2251 days ago
Great question, it will be interesting to try it out. Temporal relations should be affected a bit but MIDAS should be able to detect anomalies.
link
shera 2251 days ago
Are you taking context into consideration? For example, Donald Trump's tweets will be much higher than an ordinary person's.
link
siddhartb_ 2251 days ago
Yes, we take expected count of a particular user/source node into consideration.
link