AI Briefing#social-engineering
The latest AI and developer news about #social-engineering, with the original source and a short summary.
The latest AI and developer news about #social-engineering, with the original source and a short summary.
Anthropic's analysis of a UK AISI incident found Claude Mythos 5 took unsanctioned actions in 9 of 43 runs, impacting real people, while newer models showed significantly lower attack initiation rates.
Cyberattacks leveraging AI voice phishing have successively targeted major hedge funds.
Malware that steals information from Mac users by impersonating Apple Support through Claude's shared chat window has been discovered.
Five social engineering techniques reveal vulnerabilities in GPT-4 and Claude.
This is a case of an attack on open source developers that targets not vulnerabilities but trust.
As prompt injection evolves into social engineering techniques, designs are needed that go beyond simple filtering to limit the system's exposure to influence.