You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by sp...@apache.org on 2022/10/15 02:39:45 UTC
svn commit: r1904593 [2/2] - in /spamassassin/trunk/rulesrc/scores: 72_scores.cf scores-set0 scores-set1 scores-set2 scores-set3 stats-set0 stats-set1
Modified: spamassassin/trunk/rulesrc/scores/scores-set3
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rulesrc/scores/scores-set3?rev=1904593&r1=1904592&r2=1904593&view=diff
==============================================================================
--- spamassassin/trunk/rulesrc/scores/scores-set3 (original)
+++ spamassassin/trunk/rulesrc/scores/scores-set3 Sat Oct 15 02:39:45 2022
@@ -2,74 +2,74 @@
# ham-net-ena-week0.r1904451.log ham-net-ena-week1.r1904451.log ham-net-ena-week2.r1904451.log ham-net-ena-week3.r1904451.log ham-net-ena-week4.r1904451.log ham-net-giovanni-ham.r1904451.log ham-net-giovanni-spammy.r1904451.log ham-net-giovanni-spam.r1904451.log ham-net-grenier.r1904451.log ham-net-hege.r1904451.log ham-net-jhardin.r1904451.log ham-net-llanga.r1904451.log ham-net-mmiroslaw-mails-ham.r1904451.log ham-net-mmiroslaw-mails-spam.r1904451.log ham-net-thendrikx.r1904451.log ham-net-tsz-spam-corpus.r1904451.log spam-net-ena-week0.r1904451.log spam-net-ena-week1.r1904451.log spam-net-ena-week2.r1904451.log spam-net-ena-week3.r1904451.log spam-net-ena-week4.r1904451.log spam-net-giovanni-ham.r1904451.log spam-net-giovanni-spammy.r1904451.log spam-net-giovanni-spam.r1904451.log spam-net-grenier.r1904451.log spam-net-hege.r1904451.log spam-net-jhardin.r1904451.log spam-net-llanga.r1904451.log spam-net-mmiroslaw-mails-ham.r1904451.log spam-net-mmiroslaw-mails-spam.r1904451.log s
pam-net-thendrikx.r1904451.log spam-net-tsz-spam-corpus.r1904451.log
score AC_BR_BONANZA 0.001
-score AC_DIV_BONANZA 0.001 # force non-zero
+score AC_DIV_BONANZA 0.001
score AC_FROM_MANY_DOTS 2.999
-score AC_HTML_NONSENSE_TAGS 1.999
-score ADMITS_SPAM 2.600
+score AC_HTML_NONSENSE_TAGS 2.000
+score ADMITS_SPAM 2.599
score ADVANCE_FEE_2_NEW_FORM 1.999
score ADVANCE_FEE_2_NEW_MONEY 0.001
score ADVANCE_FEE_3_NEW 3.499
score ADVANCE_FEE_3_NEW_MONEY 2.499
-score ADVANCE_FEE_4_NEW 1.556
+score ADVANCE_FEE_4_NEW 1.573
score ADVANCE_FEE_4_NEW_MONEY 0.001
score ADVANCE_FEE_5_NEW 2.399
score ADVANCE_FEE_5_NEW_FRM_MNY 0.001
-score ADVANCE_FEE_5_NEW_MONEY 0.001
+score ADVANCE_FEE_5_NEW_MONEY 0.001 # force non-zero
score AD_PREFS 0.499
-score ALIBABA_IMG_NOT_RCVD_ALI 2.324
+score ALIBABA_IMG_NOT_RCVD_ALI 0.913
score AMAZON_IMG_NOT_RCVD_AMZN 0.001
score AXB_XMAILER_MIMEOLE_OL_024C2 0.001
-score AXB_X_FF_SEZ_S 2.054
-score BIGNUM_EMAILS_FREEM 1.796
+score AXB_X_FF_SEZ_S 2.053
+score BIGNUM_EMAILS_FREEM 1.516
score BIGNUM_EMAILS_MANY 2.999
-score BITCOIN_EXTORT_01 4.999
-score BITCOIN_MALF_HTML 0.110
+score BITCOIN_EXTORT_01 4.672
+score BITCOIN_MALF_HTML 0.311
score BITCOIN_MALWARE 0.001
-score BITCOIN_SPAM_02 0.654
+score BITCOIN_SPAM_02 1.463
score BITCOIN_SPAM_03 2.499
-score BITCOIN_SPAM_05 1.958
+score BITCOIN_SPAM_05 1.499
score BITCOIN_XPRIO 0.001
score BITCOIN_YOUR_INFO 1.415
-score BODY_URI_ONLY 1.770
+score BODY_URI_ONLY 1.769
score BOGUS_MIME_VERSION 3.499
-score BOGUS_MSM_HDRS 1.934
-score CK_HELO_GENERIC 0.001 # force non-zero
-score CONTENT_AFTER_HTML 0.427
-score CTE_8BIT_MISMATCH 0.001
+score BOGUS_MSM_HDRS 2.809
+score CK_HELO_GENERIC 0.001
+score CONTENT_AFTER_HTML 0.153
+score CTE_8BIT_MISMATCH 0.001 # force non-zero
score DATE_IN_FUTURE_Q_PLUS 2.399
-score DEAR_BENEFICIARY 1.137
+score DEAR_BENEFICIARY 1.135
score DKIMWL_WL_HIGH -0.001
score DKIMWL_WL_MED -0.001 # force non-zero
score DKIMWL_WL_MEDHI -0.001
score DX_TEXT_03 0.999
score DYNAMIC_IMGUR 3.999
-score ENCRYPTED_MESSAGE -1.000
+score ENCRYPTED_MESSAGE -0.999
score END_FUTURE_EMAILS 2.499
score FILL_THIS_FORM 1.223
-score FONT_INVIS_DIRECT 0.462
+score FONT_INVIS_DIRECT 0.083
score FONT_INVIS_HTML_NOHTML 2.999
-score FONT_INVIS_LONG_LINE 3.000
-score FONT_INVIS_MSGID 1.700
-score FONT_INVIS_NORDNS 2.228
-score FONT_INVIS_POSTEXTRAS 2.184
+score FONT_INVIS_LONG_LINE 2.999
+score FONT_INVIS_MSGID 1.250
+score FONT_INVIS_NORDNS 1.815
+score FONT_INVIS_POSTEXTRAS 2.183
score FORGED_SPF_HELO 0.170
score FORM_FRAUD_5 2.699
-score FOUND_YOU 2.183
+score FOUND_YOU 1.010
score FREEMAIL_FORGED_FROMDOMAIN 0.249
-score FROM_2_EMAILS_SHORT 3.000
+score FROM_2_EMAILS_SHORT 2.999
score FROM_FMBLA_NEWDOM 0.001
-score FROM_FMBLA_NEWDOM28 0.564
-score FROM_GOV_DKIM_AU -0.220
-score FROM_MISSPACED 1.220
+score FROM_FMBLA_NEWDOM28 0.563
+score FROM_GOV_DKIM_AU -0.318
+score FROM_MISSPACED 1.224
score FROM_MISSP_DYNIP 2.499
score FROM_MISSP_EH_MATCH 1.999
score FROM_MISSP_FREEMAIL 0.001
score FROM_MISSP_MSFT 0.001
score FROM_MISSP_SPF_FAIL 0.001
score FROM_MISSP_USER 0.001
-score FROM_MULTI_NORDNS 1.205
-score FROM_PAYPAL_SPOOF 1.115
-score FROM_SUSPICIOUS_NTLD 0.082
+score FROM_MULTI_NORDNS 1.357
+score FROM_PAYPAL_SPOOF 0.435
+score FROM_SUSPICIOUS_NTLD 0.213
score FROM_SUSPICIOUS_NTLD_FP 1.999
score FSL_BULK_SIG 0.001
score FSL_CTYPE_WIN1251 0.001
@@ -77,131 +77,130 @@ score FSL_NEW_HELO_USER 0.0
score FUZZY_AMAZON 2.699
score GB_BITCOIN_CP 2.999
score GB_FAKE_RF_SHORT 1.999
-score GB_FREEMAIL_DISPTO 0.166
-score GB_HASHBL_BTC 3.079
-score GB_URI_FLEEK_STO_HTM 0.999
+score GB_FREEMAIL_DISPTO 0.167
+score GB_HASHBL_BTC 2.664
+score GB_URI_FLEEK_STO_HTM 1.000
score GOOG_REDIR_NORDNS 3.299
score GOOG_STO_NOIMG_HTML 2.999
-score HAS_X_OUTGOING_SPAM_STAT 1.329
+score HAS_X_OUTGOING_SPAM_STAT 1.333
score HDRS_LCASE_IMGONLY 0.099
-score HDRS_MISSP 2.008
+score HDRS_MISSP 2.013
score HDR_ORDER_FTSDMCXX_DIRECT 0.001
score HDR_ORDER_FTSDMCXX_NORDNS 0.001
score HEADER_FROM_DIFFERENT_DOMAINS 0.250
-score HELO_NO_DOMAIN 0.162
+score HELO_NO_DOMAIN 0.164
score HK_LOTTO 0.999
-score HK_NAME_MR_MRS 0.999
+score HK_NAME_MR_MRS 1.000
score HK_RANDOM_ENVFROM 0.999
score HK_RANDOM_FROM 0.999
score HK_RANDOM_REPLYTO 0.999
-score HK_SCAM 0.840
-score HOSTED_IMG_DIRECT_MX 2.750
-score HOSTED_IMG_FREEM 3.217
+score HK_SCAM 0.825
+score HOSTED_IMG_DIRECT_MX 2.952
+score HOSTED_IMG_FREEM 3.219
score HOSTED_IMG_MULTI_PUB_01 2.999
-score HTML_ENTITY_ASCII 2.879
+score HTML_ENTITY_ASCII 2.738
score HTML_FONT_TINY_NORDNS 1.999
score HTML_OFF_PAGE 2.999
-score HTML_SINGLET_MANY 1.652
+score HTML_SINGLET_MANY 1.650
score HTML_TAG_BALANCE_CENTER 3.699
-score HTML_TEXT_INVISIBLE_FONT 0.409
-score HTML_TEXT_INVISIBLE_STYLE 3.203
-score JH_SPAMMY_HEADERS 3.500
+score HTML_TEXT_INVISIBLE_FONT 0.527
+score HTML_TEXT_INVISIBLE_STYLE 3.211
+score JH_SPAMMY_HEADERS 3.499
score KHOP_HELO_FCRDNS 0.399
score LIST_PARTIAL_SHORT_MSG 2.499
score LONGLN_LOW_CONTRAST 1.446
-score LONG_HEX_URI 1.518
-score LONG_IMG_URI 0.868
-score LONG_INVISIBLE_TEXT 0.650
+score LONG_HEX_URI 1.523
+score LONG_IMG_URI 0.737
+score LONG_INVISIBLE_TEXT 0.642
score LOTS_OF_MONEY 0.010
-score LOTTO_DEPT 0.958
-score MALWARE_NORDNS 0.143
+score LOTTO_DEPT 0.875
+score MALWARE_NORDNS 0.558
score MILLION_HUNDRED 0.001
score MIMEOLE_DIRECT_TO_MX 0.001
score MIME_NO_TEXT 1.999
-score MIXED_ES 2.200
-score MIXED_HREF_CASE 1.339
+score MIXED_ES 2.199
+score MIXED_HREF_CASE 1.344
score MONEY_ATM_CARD 0.001
score MONEY_FORM 0.001
score MONEY_FORM_SHORT 2.499
-score MONEY_FRAUD_3 0.105
+score MONEY_FRAUD_3 0.106
score MONEY_FRAUD_5 2.699
-score MONEY_FRAUD_8 2.799
-score MONEY_FREEMAIL_REPTO 1.462
+score MONEY_FRAUD_8 2.800
+score MONEY_FREEMAIL_REPTO 1.460
score MONEY_FROM_MISSP 0.001
score MSMAIL_PRI_ABNORMAL 0.001
-score NA_DOLLARS 0.641
-score NICE_REPLY_A -2.856
-score NORDNS_LOW_CONTRAST 0.001 # force non-zero
-score NO_FM_NAME_IP_HOSTN 0.001
-score NSL_RCVD_FROM_USER 0.001
-score NSL_RCVD_HELO_USER 1.269
-score NUMBERONLY_BITCOIN_EXP 1.749
-score OBFU_TEXT_ATTACH 0.191
-score ODD_FREEM_REPTO 2.703
+score NA_DOLLARS 0.644
+score NICE_REPLY_A -2.961
+score NORDNS_LOW_CONTRAST 0.001
+score NO_FM_NAME_IP_HOSTN 0.001 # force non-zero
+score NSL_RCVD_FROM_USER 0.001 # force non-zero
+score NSL_RCVD_HELO_USER 0.392
+score NUMBERONLY_BITCOIN_EXP 0.001
+score OBFU_TEXT_ATTACH 0.675
+score ODD_FREEM_REPTO 2.735
score PDS_BTC_ID 0.499
score PDS_BTC_MSGID 0.001
-score PDS_HELO_SPF_FAIL 1.999
+score PDS_HELO_SPF_FAIL 1.247
score PDS_NAKED_TO_NUMERO 1.999
score PDS_NO_FULL_NAME_SPOOFED_URL 0.749
score PDS_RDNS_DYNAMIC_FP 0.010
-score PDS_SHORT_BOGUS_MSM_HDRS 0.458
+score PDS_SHORT_BOGUS_MSM_HDRS 1.213
score PDS_SHORT_SPOOFED_URL 1.999
score PDS_TONAME_EQ_TOLOCAL_FREEM_FORGE 0.001
score PHP_ORIG_SCRIPT 2.499
-score PHP_SCRIPT 0.983
-score PP_MIME_FAKE_ASCII_TEXT 0.001 # force non-zero
+score PHP_SCRIPT 0.981
+score PP_MIME_FAKE_ASCII_TEXT 0.001
score RAND_MKTG_HEADER 1.999
-score RATWARE_NO_RDNS 2.279
-score RCVD_IN_MSPIKE_H2 -0.001
-score RDNS_NUM_TLD_XM 2.207
-score REPTO_419_FRAUD 0.001
-score SCC_CANSPAM_2 3.222
-score SCC_ISEMM_LID_1A 2.530
-score SCC_ISEMM_LID_1B 0.844
+score RATWARE_NO_RDNS 2.118
+score RCVD_IN_MSPIKE_H2 -0.001 # force non-zero
+score RDNS_NUM_TLD_XM 2.775
+score REPTO_419_FRAUD 0.001 # force non-zero
+score SCC_CANSPAM_2 3.138
+score SCC_ISEMM_LID_1A 2.903
+score SCC_ISEMM_LID_1B 0.846
score SCC_THREE_WORD_MONTY 2.599
-score SENDGRID_REDIR 1.500
-score SERGIO_SUBJECT_VIAGRA01 2.821
-score SHOPIFY_IMG_NOT_RCVD_SFY 0.080
-score SPOOFED_FREEMAIL 0.001
+score SENDGRID_REDIR 1.499
+score SERGIO_SUBJECT_VIAGRA01 0.966
+score SHOPIFY_IMG_NOT_RCVD_SFY 0.077
+score SPOOFED_FREEMAIL 0.001 # force non-zero
score SPOOFED_FREEMAIL_NO_RDNS 0.001
score SPOOFED_FREEM_REPTO 2.499
-score SPOOF_GMAIL_MID 0.001
+score SPOOF_GMAIL_MID 0.001 # force non-zero
score STATIC_XPRIO_OLE 0.001
score THIS_AD 0.799
score TO_EQ_FM_DOM_SPF_FAIL 0.001
-score TO_EQ_FM_SPF_FAIL 0.001 # force non-zero
+score TO_EQ_FM_SPF_FAIL 0.001
score TO_NO_BRKTS_FROM_MSSP 2.499
score TO_NO_BRKTS_HTML_IMG 1.999
score TO_NO_BRKTS_HTML_ONLY 1.999
-score TO_NO_BRKTS_NORDNS_HTML 1.855
-score TO_NO_BRKTS_PCNT 0.935
+score TO_NO_BRKTS_NORDNS_HTML 1.854
+score TO_NO_BRKTS_PCNT 2.174
score TVD_APPROVED 2.574
-score TVD_RCVD_SPACE_BRACKET 2.486
-score TVD_SPACE_RATIO_MINFP 0.001
-score UNDISC_FREEM 3.099
-score UNDISC_MONEY 2.445
+score TVD_RCVD_SPACE_BRACKET 2.181
+score TVD_SPACE_ENCODED 0.001
+score UNDISC_FREEM 3.100
+score UNDISC_MONEY 2.453
score UNICODE_OBFU_ASC 2.499
-score UPPERCASE_URI 0.229
+score UPPERCASE_URI 0.629
score URI_DOTEDU 1.999
-score URI_FIREBASEAPP 3.000
+score URI_FIREBASEAPP 2.999
score URI_GOOGLE_PROXY 0.700
-score URI_OBFU_DOM 2.299
-score URI_PHISH 3.697
-score URI_PHP_REDIR 3.300
-score URI_TRY_3LD 1.668
+score URI_PHISH 3.698
+score URI_PHP_REDIR 3.299
+score URI_TRY_3LD 1.672
score URI_WPADMIN 2.399
score URI_WP_HACKED 3.499
-score URI_WP_HACKED_2 2.500
-score VFY_ACCT_NORDNS 2.999
-score WORD_INVIS 0.242
+score URI_WP_HACKED_2 2.499
+score VFY_ACCT_NORDNS 2.677
+score WORD_INVIS 0.693
score WORD_INVIS_MANY 2.999
-score XFER_LOTSA_MONEY 0.999
+score XFER_LOTSA_MONEY 1.000
score XM_RANDOM 2.499
-score XM_RECPTID 3.000
+score XM_RECPTID 2.999
score XPRIO 0.001
-score XPRIO_SHORT_SUBJ 0.320
+score XPRIO_SHORT_SUBJ 1.945
score YOUR_DELIVERY_ADDRESS 1.249
-score YOU_INHERIT 1.576
+score YOU_INHERIT 1.578
score AC_POST_EXTRAS 1.000
score AC_SPAMMY_URI_PATTERNS1 1.000
score AC_SPAMMY_URI_PATTERNS10 1.000
@@ -299,6 +298,7 @@ score LIST_PRTL_SAME_USER 1.0
score LUCRATIVE 1.000
score MALF_HTML_B64 1.000
score MALWARE_PASSWORD 1.000
+score MANY_HDRS_LCASE 0.100
score MIXED_AREA_CASE 1.000
score MIXED_CENTER_CASE 1.000
score MIXED_FONT_CASE 1.000
Modified: spamassassin/trunk/rulesrc/scores/stats-set0
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rulesrc/scores/stats-set0?rev=1904593&r1=1904592&r2=1904593&view=diff
==============================================================================
--- spamassassin/trunk/rulesrc/scores/stats-set0 (original)
+++ spamassassin/trunk/rulesrc/scores/stats-set0 Sat Oct 15 02:39:45 2022
@@ -1,40 +1,40 @@
##### WITH NEW RULES AND SCORES #####
# SUMMARY for threshold 5.0:
-# Correctly non-spam: 220834 70.688% (99.604% of non-spam corpus)
-# Correctly spam: 61900 19.814% (68.251% of spam corpus)
-# False positives: 878 0.281% (0.396% of nonspam, 12600 weighted)
-# False negatives: 28794 9.217% (31.749% of spam, 45123 weighted)
-# Average score for spam: 10.0 nonspam: 0.6
+# Correctly non-spam: 233101 71.339% (99.611% of non-spam corpus)
+# Correctly spam: 63997 19.586% (69.009% of spam corpus)
+# False positives: 911 0.279% (0.389% of nonspam, 12598 weighted)
+# False negatives: 28740 8.796% (30.991% of spam, 44865 weighted)
+# Average score for spam: 10.3 nonspam: 0.6
# Average for false-pos: 7.0 false-neg: 1.6
-# TOTAL: 312406 100.00%
+# TOTAL: 326749 100.00%
Reading scores from "tmprules"...
Reading per-message hit stat logs and scores...
# SUMMARY for threshold 5.0:
-# Correctly non-spam: 27614 99.56%
-# Correctly spam: 7843 68.43%
-# False positives: 123 0.44%
-# False negatives: 3619 31.57%
-# TCR(l=50): 1.173303 SpamRecall: 68.426% SpamPrec: 98.456%
+# Correctly non-spam: 29194 99.64%
+# Correctly spam: 8128 69.35%
+# False positives: 106 0.36%
+# False negatives: 3593 30.65%
+# TCR(l=50): 1.318003 SpamRecall: 69.346% SpamPrec: 98.713%
##### WITHOUT NEW RULES AND SCORES #####
Reading scores from "../rules-base"...
Reading per-message hit stat logs and scores...
# SUMMARY for threshold 5.0:
-# Correctly non-spam: 215098 97.02%
-# Correctly spam: 55959 61.70%
-# False positives: 6614 2.98%
-# False negatives: 34735 38.30%
-# TCR(l=50): 0.248181 SpamRecall: 61.701% SpamPrec: 89.430%
+# Correctly non-spam: 227376 97.16%
+# Correctly spam: 57785 62.31%
+# False positives: 6636 2.84%
+# False negatives: 34952 37.69%
+# TCR(l=50): 0.252860 SpamRecall: 62.311% SpamPrec: 89.699%
Reading scores from "../rules-base"...
Reading per-message hit stat logs and scores...
# SUMMARY for threshold 5.0:
-# Correctly non-spam: 26951 97.17%
-# Correctly spam: 7066 61.65%
-# False positives: 786 2.83%
-# False negatives: 4396 38.35%
-# TCR(l=50): 0.262312 SpamRecall: 61.647% SpamPrec: 89.990%
+# Correctly non-spam: 28527 97.36%
+# Correctly spam: 7400 63.13%
+# False positives: 773 2.64%
+# False negatives: 4321 36.87%
+# TCR(l=50): 0.272765 SpamRecall: 63.135% SpamPrec: 90.542%
Modified: spamassassin/trunk/rulesrc/scores/stats-set1
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rulesrc/scores/stats-set1?rev=1904593&r1=1904592&r2=1904593&view=diff
==============================================================================
--- spamassassin/trunk/rulesrc/scores/stats-set1 (original)
+++ spamassassin/trunk/rulesrc/scores/stats-set1 Sat Oct 15 02:39:45 2022
@@ -1,11 +1,11 @@
##### WITH NEW RULES AND SCORES #####
# SUMMARY for threshold 5.0:
-# Correctly non-spam: 285867 68.459% (99.613% of non-spam corpus)
-# Correctly spam: 103509 24.788% (79.259% of spam corpus)
-# False positives: 1110 0.266% (0.387% of nonspam, 39382 weighted)
-# False negatives: 27087 6.487% (20.741% of spam, 52288 weighted)
-# Average score for spam: 15.8 nonspam: -0.8
+# Correctly non-spam: 285864 68.458% (99.612% of non-spam corpus)
+# Correctly spam: 103510 24.788% (79.260% of spam corpus)
+# False positives: 1113 0.267% (0.388% of nonspam, 39453 weighted)
+# False negatives: 27086 6.487% (20.740% of spam, 52190 weighted)
+# Average score for spam: 15.4 nonspam: -0.8
# Average for false-pos: 7.8 false-neg: 1.9
# TOTAL: 417573 100.00%
@@ -14,10 +14,10 @@ Reading per-message hit stat logs and sc
# SUMMARY for threshold 5.0:
# Correctly non-spam: 35749 99.60%
-# Correctly spam: 13073 79.79%
+# Correctly spam: 13071 79.77%
# False positives: 143 0.40%
-# False negatives: 3312 20.21%
-# TCR(l=50): 1.566144 SpamRecall: 79.786% SpamPrec: 98.918%
+# False negatives: 3314 20.23%
+# TCR(l=50): 1.565845 SpamRecall: 79.774% SpamPrec: 98.918%
##### WITHOUT NEW RULES AND SCORES #####
Reading scores from "../rules-base"...