At the 2023 Defcon hacker conference, Humane Intelligence in partnership with AI transparency groups and US government support, initiated a red-teaming exercise targeting generative AI platforms. Inviting US residents to join the NIST's ARIA challenge, it enhances scrutiny on opaque AI systems. The exercise aims to rigorously test the security, resilience, and ethics of these technologies. This broad community participation, including traditionally underrepresented groups, will inform scientific evaluation and promote algorithmic transparency and accountability via competitive red teaming events.
Source: https://www.wired.com/story/nist-humane-intelligence-generative-ai-red-team-contest/
TPRM report: https://scoringcyber.rankiteo.com/company/humaneintelligence
"id": "hum000082324",
"linkid": "humaneintelligence",
"type": "Vulnerability",
"date": "8/2024",
"severity": "25",
"impact": "1",
"explanation": "Attack without any consequences"{'affected_entities': [{'industry': 'Artificial Intelligence',
'name': 'Generative AI Platforms',
'type': 'Technology'}],
'description': 'Humane Intelligence, in partnership with AI transparency '
'groups and US government support, initiated a red-teaming '
'exercise targeting generative AI platforms at the 2023 Defcon '
'hacker conference. The exercise aims to test the security, '
'resilience, and ethics of these technologies through '
'competitive red teaming events.',
'impact': {'systems_affected': 'Generative AI platforms'},
'motivation': 'Enhance scrutiny on opaque AI systems, promote algorithmic '
'transparency and accountability',
'references': [{'source': 'Defcon 2023'}],
'response': {'third_party_assistance': 'AI transparency groups, US government '
'support'},
'title': 'Red-Teaming Exercise at Defcon 2023',
'type': 'Red-Teaming Exercise'}