DNN targeting mechanism; not LLM: IBM DeepLocker demonstration
Review CAT-X03 · Catalogue X03
EXCLUDED — proof of concept. Researchers built a demonstration. Neural targeting is not a rogue LLM choosing to hack.
Reviewed: Not recorded · Rule: external-intrusion-v1
Evidence status
EXCLUDED — proof of concept
Dates and discovery
- Incident date
- Black Hat USA, August 2018
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- Not recorded
- Discovery channel
- Not recorded
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- IBM Research — DeepLocker (Black Hat USA 2018)Original account · research.ibm.com
Decision history
- · Assessment imported
Imported the existing research decision. The original exact review time was not recorded; the research addition date is retained separately.
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.