Adversarial Misuse of Generative AI

2025-01-29 Google

https://cloud.google.com/blog/topics/threat-intelligence/adversarial-misuse-generative-ai

Thumbnail for Adversarial Misuse of Generative AI

Google Threat Intelligence Group examined how government-backed APT and information-operations actors attempted to use Gemini for operational support. The source says actors used the tool mainly for research, troubleshooting, content generation, localization, infrastructure research, reconnaissance, vulnerability research, payload development, and scripting assistance. GTIG did not observe novel AI-enabled attack techniques or successful prompt attacks, and it says Gemini did not produce malware or other content that could plausibly enable a successful malicious campaign in the reviewed activity.

Related Actors

Related Reports

2025-02-12 • 60% Match
#APT43 #T1102.002 #T1082 #T1059.003 #T1567.002 #T1140 #T1005 #T1070.004 #T1587.001 #T1041 #T1608.001 #T1071.001 #T1112 #T1083 #T1056.001 #T1059.006 #T1204.001 #T1059.007 #T1036 #T1027 #T1204.002 #T1566.002 #T1555.003 #T1057 #T1059.005 #T1583.006 #T1518.001 #T1566.001 #T1547.001 #T1585.002 #T1053.005 #T1598.003 #T1583.001 #T1059.001 #T1036.005 #T1552.001 #T1585.001 #T1105 #T1219 #T1055 #T1553.002 #T1562.001 #T1027.002 #T1133 #T1190 #T1098 #T1016 #T1074.001 #T1588.002 #T1055.012 #T1587 #T1078.003 #T1071.002 #T1562.004 #T1550.002 #T1111 #T1071.003 #T1591 #T1003.001 #T1218.011 #T1593.002 #T1586.002 #T1588.005 #T1583.004 #T1036.004 #T1589.003 #T1594 #T1218.010 #T1557 #T1593.001 #T1218.005 #T1589.002 #T1584.001 #T1070.006 #T1021.001 #T1560.001 #T1176 #T1136.001 #T1543.003 #T1012 #T1534 #T1560.003 #T1007 #T1564.003 #T1114.003 #T1114.002 #T1564.002 #T1040 #T1546.001 #T1505.003
Shares tag: APT43 • Published within a month
« Back