security1 publisher
Safe code fooled all 12 models AWS tested in its Deception Benchmark
AWS has published a 14,822-sample set that pairs real vulnerability patterns with controls that stop them. With direct prompting the 12 models it scored flagged between 41% and 99% of safe samples as exploitable.
Publishers:helpnetsecurity.com
Reality
- Evidence58
- Adoption18
- Hype gap+15
- Incentives65
- Confidence57