๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

cv usk
@cv_usk
AI / Software Research Notes AI Agent, LLMOps, MLOps, Software Architecture ๆŠ•็จฟใฏๅ€‹ไบบใฎๆ„่ฆ‹ใงใ™ใ€‚
๊ฐ€์ž… May 2026
284 ํŒ”๋กœ์ž‰ ์ค‘    451 ํŒฌ
TL;DR: Instead of hunting vulnerabilities one by one, shrink the code that can be reached. Claude analyzed 25 open-source projects, reported 493 issues, and cut about 16% of OpenSSH's pre-authentication code. Title: Using Claude to reduce the attack surface of code URL: Key points ใƒป๐Ÿ—บ๏ธ 25 projects and 5M+ lines, with 17,000+ config options inventoried (3,842 security-relevant) ใƒป๐Ÿ”“ 93 unnecessary pre-auth surfaces in default configs, plus 61 combos that silently weaken a pre-auth control ใƒปโš™๏ธ 162 option combinations accepted with no warning, 94 of them silently disabling a security control ใƒป๐ŸŒ Hostname-based rules relying on reverse DNS fail open when it's off (4 projects) ใƒปโณ A config conflict dropped a certificate requirement for 21 years, undocumented ใƒป๐Ÿ” OpenSSH: about 4,500 lines of experimental ML-DSA-44 code reachable by unauthenticated clients removed, shipped in 10.6 Making unknown bugs unreachable seems more practical than fixing them one at a time. #AISecurity# #OpenSSH#
๋” ๋ณด๊ธฐ