DrWhax

@drwhax@infosec.exchange · Joined ⁨Nov⁩ ⁨2022⁩

professional troublemaker

Hart voor Internetvrijheid
hviv.nl/
Languages
NL/EN/ES
GPG
0x2C9686C23DF31CBF602F2906748800B2AB826D05

Replying to @⁨wolf480pl@mstdn.io⁩

@wolf480pl sometimes, sometimes they don't, sometimes one finds a better way to chain vulnerabilities to achieve a certain objective. It all depends a bit on the harness as well, lots of small knobs to twist.

Some benchmarks are available on: exploitbench.ai/

ExploitBench: Real exploitation is a ladder. Capability-graded V8 exploit benchmark.ExploitBenchExploitBenchHow far up the exploitation ladder can an agent climb on a production JS engine? ExploitBench measures frontier LLMs on full-control V8 exploit synthesis with 16 capabilities measured per run and multi-round shuffled-layout grading.