Autonomous intelligent agents offer a transformative approach to cyber defense by operating independently in complex and dynamic environments. While much research has focused on …
The widespread adoption of large language models (LLMs) for code generation has introduced significant security risks, as these models relatively frequently produce code containing …
Model stealing attacks have been successfully used in many machine learning domains, but there is little understanding of how these attacks work against models that perform malware …
As machine learning becomes more widely used, the need to study its implications in security and privacy becomes more urgent. Research on the security aspects of machine learning, …