Differences

This shows you the differences between two versions of the page.

--- malicious_url_detection [2025/06/25 10:39]
60.168.209.12 old revision restored (2025/06/18 07:45)
+++ malicious_url_detection [2025/06/25 10:42] (current)
60.168.209.12 old revision restored (2025/06/17 00:33)
@@ Line 1: / Line 1: @@
 ====== Introduction ======
-  * Member : 蔡昀達, Cayon Liow
+  * Member : 蔡昀達, 廖其忻
   * Meeting :
@@ Line 7: / Line 7: @@
 ^Name^Mail^
 |蔡昀達|bb04902103@gmail.com|
-|Cayon Liow| |
+|廖其忻|cayon.1318.96@hotmail.com |
+|尹聖翔|b06902103@ntu.edu.tw |
@@ Line 51: / Line 52: @@
 White List
 - https://www.alexa.com/topsites
-- https://otx.alienvault.com/
-- https://www.riskiq.com/platform/architecture/internet-data-sets/passive-dns/
-- https://www.abuseipdb.com/
 - Chrome外掛軟體 Googel WOT plugin
@@ Line 70: / Line 64: @@
 - https://www.apivoid.com/api/domain-reputation/
+#####
+Black List (目前沒有可利用的資料)
+- (主要是查IP)https://www.abuseipdb.com/
+- (主要是Domain Name，僅參考)https://www.riskiq.com/platform/architecture/internet-data-sets/passive-dns/
+- (黑名單太少，參考用)https://otx.alienvault.com/
 ======  Meeting ======
+===== 09/23 progress =====
+  - tfidf results
+    - accuracy : 98.3%
+  - model explain mechanism
+    - implemented : highlight  trigger pattern
+    - results1 (tree interpreter):
+    {{:dada.1.png}}
+    - results2 (lime interpreter):
+    {{:dada.2.png}}
+^Year^Venue^Title^Link^Assign^
+|2016|ACM|LIME:Why should i trust you?: Explaining the predictions of any classifier|[[https://www.kdd.org/kdd2016/papers/files/rfp0573-ribeiroA.pdf|PDF]]| |
+|2014|KAIS|Shapley sampling values:Explaining prediction models and individual predictions with feature contributions|[[|PDF]]| |
+|2017|arxiv|DeepLIFT:Learning important features through propagating activation differences|[[|PDF]]| |
+|2016|IEEE SP|QII:Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems|[[|PDF]]| |
+|2015|PLoS ONE|Layer-wise relevance propagation:On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation|[[|PDF]]| |
+|2010|PLoS ONE|Shapley regression values:Analysis of regression in game theory approach|[[|PDF]]| |
+===== 09/16 =====
+  - check basline CNN model has high accuracy
+  - build tfidf model
+  - build explain feature
+    - triggered pattern
+    - malicious url family matching
+  - phishing url survey

mslab

User Tools

Site Tools

Differences

Page Tools