src_7b6d9b94ad4ba18620
- Source-provided label
- Not reported
- Evidence class
- mentioned in report
- Confidence
- Not reported
- Observed
- Aug 12, 2026 09:04 UTC
- Retrieved
- Oct 08, 2026 03:48 UTC
Can AI invent new attack techniques? New research from James Kettle and PortSwigger Research
We already know AI can find vulnerabilities. James Kettle, PortSwigger's Director of Research, wanted to answer a harder question: can an autonomous system invent genuinely new attack techniques? To f
Reference details
- Source category
- Research & news
- Report title
Can AI invent new attack techniques? New research from James Kettle and PortSwigger Research- First reported
- Aug 12, 2026 09:04 UTC
- Last reported
- Aug 12, 2026 09:04 UTC
- Catalog updated
- Oct 08, 2026 03:48 UTC
- Record ID
984a026a1a52fe0358eb6de7afea80c38c0c63adaf0be3b47f7238e465881881
Published indicators
Network indicators are visibly defanged. This page does not make them clickable or send them to another service.
No validated file hashes or network indicators are stored for this record.
Source observations
This record contains metadata and attribution only. It does not host, download, unpack, render, or execute malware samples.
Feed collection status
Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.
1 sources: 0 stale, 0 needing attention, 0 paused, 1 unverified.
Review source update dates and status
- src_7b6d9b94ad4ba18620Collection status unverifiedLast successful batch: Unverified
Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.