all InfoSec news
When to Trust AI: Advances and Challenges for Certification of Neural Networks. (arXiv:2309.11196v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Artificial intelligence (AI) has been advancing at a fast pace and it is now
poised for deployment in a wide range of applications, such as autonomous
systems, medical diagnosis and natural language processing. Early adoption of
AI technology for real-world applications has not been without problems,
particularly for neural networks, which may be unstable and susceptible to
adversarial examples. In the longer term, appropriate safety assurance
techniques need to be developed to reduce potential harm due to avoidable
system failures …
adoption applications artificial artificial intelligence autonomous certification challenges deployment diagnosis fast intelligence language medical natural natural language natural language processing networks neural networks problems systems technology trust world