Repository navigation
Sync score-adjusted rules after Sova corpus update - #85
Merged
Merged
Conversation
The malware corpus now includes 14 Sova samples, so score_adjustment retrained the whole rule pool against it. This commit carries the resulting weights for 272 rules. Only the score field changes; crime descriptions, API pairs, permissions, and labels are untouched. Sova itself ships no new rule. Two candidates were drafted and trained, and both were rejected: a clipboard-overwrite pair (ClipData.newPlainText + ClipboardManager.setPrimaryClip) trained to -1.74 because legitimate apps use the same pair, and an icon-hiding pair duplicated the existing rule ev-flow#79. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The malware corpus now includes 14 Sova samples (MITRE S1062), so
score_adjustmentretrained the whole rule pool against it. This PR carries the resulting weights for 272 rules.Only the
scorefield changes — crime descriptions, API pairs, permissions, and labels are untouched. Verified: every changed line in the diff is a"score"line.No new rule for Sova
Two candidate rules were drafted from the Sova samples and trained. Both were rejected:
ClipData.newPlainText+ClipboardManager.setPrimaryClipgetPackageManager+setComponentEnabledSettingSova's report therefore rests on existing rules and is published separately in ev-flow/quark-engine#957.
Sample verification
Quark flagged 14 of 14 Sova samples as high-risk with these weights (detection rate 100%).