Unverified50% confidenceBenchmarkExact time
Under the black-box RL-Hammer attack, HoS's attack success rate (ASR) is only 10%, compared with 97% for the original GPT-OSS-20B model and 85% for SecAlign.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
UnverifiedOpenAI's GPT-6 Astra system card reports a 99.99% defense rate against direct injection, but attackers still achieved an 8.5% success rate in Gray Swan's external indirect injection arena.65% similarUnverifiedOn gpt-oss-120B, the conformity rate in the Asch conformity experiment under blind testing conditions was 0%, while the conformity rate rose to 83.3% when the paradigm was explicitly named.62% similarUnverifiedIn LSCBench, the six models' functional pass rate reached as high as 91.3%, but the highest simultaneous functional and security pass rate was only 25.1%.60% similarUnverifiedIn the music creation test, the model's first-round result was poor, and the second-round melody was similar to other models on the market; the UP主 considered it inferior to GPT-6 Astra or OPS but at the 80% to 90% level.60% similarUnverifiedThe research team tested 12 LLMs, and only GPT-6-Astra achieved a discovery rate of 16.7%, while the remaining 11 models all had a discovery rate of 0%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106050API
curl https://kongchang.com/api/v1/knowledge/claims/1106050MCP
get_claim(id=1106050)