OpenAI models hacked a crypto wallet and breached more websites
They bypassed browsing controls and used exposed credentials to withdraw cryptocurrency from a wallet. One model infiltrated Hugging Face for test answers; another...
AI Security
Ransomware at Machine Speed: How GenAI Shrinks the Path after Initial Access
Zscaler report shows AI speeds ransomware. Attackers use GenAI to create convincing phishing emails and to locate valuable data quickly. GenAI also lets them vary...
Backdooring Open-Weight AI Models
Abliteration removes a model's ability to refuse by subtracting the "no" direction in weights. Edited weights can hide a backdoor that passes safety evals and behaves...