THREAT OPS › Threat News › GTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI
GTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI
<div class="block-paragraph_advanced"><p>Written by: Aurora Blum, Kelli Vanderlee, Jess Xia, David Mainor, Kimberly Goody</p> <hr /> <h3><span style="vertical-align: baseline;">Executive Summary</span><strong style="vertical-align: baseline;"> </strong></h3> <p><span style="vertical-align: baseline;">Since the release of our </span><a href="https://cloud.google.com/blog/topics/threat-intelligence/
Attributed threat actors
- APT42G1044
- Sandworm TeamG0034
- Mustang PandaG0129
MITRE ATT&CK techniques
- Artificial IntelligenceT1588.007
- IP AddressesT1590.005
- JavaScriptT1059.007
- VulnerabilitiesT1588.006
- Supply Chain CompromiseT1195
- Social EngineeringT1684
- MasqueradingT1036
- Process InjectionT1055
- Email AccountT1087.003
- Vulnerability ScanningT1595.002
- Password SprayingT1110.003
- Email AddressesT1589.002
- PowerShellT1059.001
- Social MediaT1593.001
- CredentialsT1589.001
- ImpersonationT1684.001
- Dynamic API ResolutionT1027.007
- AI SoftwareAML.T0010.001
- Generative AIAML.T0016.002
- ImpersonationAML.T0073
- MasqueradingAML.T0074
Indicators of compromise
- https://socket.dev/blog/ai-has-taken-over-open-sourceurl
- https://www.reversinglabs.com/blog/claude-promptmink-malware-cryptourl
- https://ai.google.dev/gemini-api/terms#:~:text=You%20may%20not%20use%20the,%28e.g.%2C%20parameter%20weights%29url
- https://ai.google/principles/#our-ai-principles-in-actionurl
- https://gemini.google/us/policy-guidelines/?hl=enurl
- https://transparency.google/our-approach/our-policy-process/url