TTPwire Vol. 1 · MITRE ATT&CK·Tagged

← All stories

SecurityWeek

Hacker Conversations: Joey Melo on Hacking AI

Kevin Townsend · 1 day ago · Read original ↗

ATT&CK techniques detected

3 predictions
T1588.001Malware
72%
“##testers, and red teamers have, or acquire, the same set of skills used by malicious hackers. while many ‘ shady ’ young hackers become legitimate members of the cybersecurity fraternity as they mature, very few then turn their back on legitimacy and sell their skills on the dar…”
T1588.002Tool
55%
“##testers, and red teamers have, or acquire, the same set of skills used by malicious hackers. while many ‘ shady ’ young hackers become legitimate members of the cybersecurity fraternity as they mature, very few then turn their back on legitimacy and sell their skills on the dar…”
T1598Phishing for Information
30%
“that path. i believe true virtue lies in having the ability to cause harm but consciously choosing not to. that ’ s the standard i hold myself to. ” learn more at the ai risk summit at the ritz - carlton, half moon bay related : hacker conversations : rachel tobac and the art of …”

Summary

AI red team specialist details his methods for manipulating AI guardrails through jailbreaking and data poisoning, helping developers harden machine learning models.

The post Hacker Conversations: Joey Melo on Hacking AI appeared first on SecurityWeek.