#prompt-injection-attacks

[ follow ]
#ai-security #phishing #microsoft-copilot #email-threats #ai-security-vulnerabilities #healthcare-ai-risks
Information security
fromTechRepublic
4 days ago

Researchers Uncover New Phishing Risk Hidden Inside Microsoft Copilot

Attacker-controlled text in emails can manipulate Microsoft Copilot summaries through cross-prompt injection attacks, inserting deceptive alerts into trusted AI interfaces that users find more convincing than suspicious emails.
Healthcare
fromTheregister
2 weeks ago

AI doctor's assistant swayed to change scrips - researchers

Healthcare AI systems can be manipulated through prompt injection techniques to bypass safety measures, reveal system instructions, and generate harmful recommendations that persist in patient records.
Artificial intelligence
fromTechCrunch
4 months ago

The glaring security risks with AI browser agents | TechCrunch

AI-powered browser agents require deep access to user accounts and pose significant privacy and prompt-injection risks that can expose or misuse personal data.
[ Load more ]