Security News > 2018 > April > Open-source library for improving security of AI systems
2018-04-18 19:50
IBM researchers have created the Adversarial Robustness Toolbox, an open-source library to help researchers improve the defenses of real-world AI systems. Attacks against neural networks have recently been flagged as one of the biggest dangers in our modern world where AI systems are increasingly getting embedded in many technologies we use and depend on daily. Adversaries can sometimes tamper with them even if they don’t know much about them, and “breaking” the system could result … More → The post Open-source library for improving security of AI systems appeared first on Help Net Security.
News URL
http://feedproxy.google.com/~r/HelpNetSecurity/~3/nUMl733Rsr0/
Related news
- AI security 2024: Key insights for staying ahead of threats (source)
- SSHamble: Open-source security testing of SSH services (source)
- Unlock the Future of Cybersecurity: Exclusive, Next Era AI Insights and Cutting-Edge Training at SANS Network Security 2024 (source)
- Scout Suite: Open-source cloud security auditing tool (source)
- The AI balancing act: Unlocking potential, dealing with security issues, complexity (source)
- AI for application security: Balancing automation with human oversight (source)
- CrowdSec: Open-source security solution offering crowdsourced protection (source)
- Two-Thirds of Security Leaders Consider Banning AI-Generated Code, Report Finds (source)
- Security leaders consider banning AI coding due to security risks (source)
- Digital Maturity Key to AI Success in Australian Cyber Security (source)