Red Teaming stories - Page 6
New report reveals major security flaws in multimodal AI models
Sat, 10th May 2025
#
genai
#
ai
#
ai models
Enkrypt AI's report reveals severe vulnerabilities in multimodal AI models, warning of safety risks from harmful prompt injections in images.
Bugcrowd Grows Global Reach via AWS ISV Accelerate
Thu, 8th May 2025
#
devops
#
hyperscale
#
cloud security
Bugcrowd joins AWS ISV Accelerate Program, enhancing global reach and co-selling to offer crowdsourced security services via AWS sales teams worldwide.
AI-powered cyberattacks surge as criminals exploit new tools
Wed, 30th Apr 2025
#
uc
#
firewalls
#
cloud security
Fortinet's 2025 report reveals a surge in AI-driven cyberattacks in 2024, urging firms to adopt proactive, intelligence-led defence strategies.
NetRise launches AI tool to spot unknown software weaknesses
Wed, 30th Apr 2025
#
manufacturing
#
supply chain
#
risk & compliance
NetRise launches ZeroLens, an AI tool that detects undisclosed software weaknesses in compiled code, aiming to prevent cyberattacks before vulnerabilities emerge.
Lasso launches automated Red Teaming for GenAI security
Fri, 28th Mar 2025
#
data protection
#
physical security
#
genai
Lasso has unveiled an automated Red Teaming solution aimed at fortifying the security of Generative AI apps by simulating real-world cyber-attacks.