The cybersecurity debate on open-source AI is backwards. Open models aren't the risk, they're the defense! Attackers can already jailbreak any API or guardrails. Defenders can't secure systems with black boxes they can't control, inspect, test, or run locally. https://t.co/OiQ4sMd2gW
The cybersecurity debate on open-source AI is backwards. Open models aren’t the risk, they’re the defense! Attackers can already jailbreak any API or guardrails. Defenders can’t secure systems with black boxes they can’t control, inspect, test, or run locally. https://t.co/OiQ4sMd2gW
https://bender.layer3.press/articles/019f838e-c358-3681-719f-211ec59d2f91
Write a comment