The document was issued by academy or academy organization.

Visible to the public AICW - The Dangers of the Subconscious Mind (of Cyber Reasoning Systems)

ABSTRACT: Humans have goals, hopes, dreams, and fears. Humans are brilliant. They make incredible intuitive inferences. They conceptualize amazing algorithms to augment cybersecurity. But they can be misled; tricked; foole d into carrying out actions counter to their own best-interests.


Visible to the public Security Against Adversarial Examples

Recent research suggests that modern machine learning methods are fragile and easily attacked, which raises concerns about their use in security-critical settings. I will survey several attacks on machine learning and directions for making machine learning more robust against attack. I will also briefly mention my own research in this area.


Visible to the public Checked C: Safe C, Incrementally

Vulnerabilities that compromise memory safety are at the heart of many attacks. Spatial safety, one aspect of memory safety, is ensured when any pointer dereference is always within the memory allocated to that pointer. Buffer overruns violate spatial safety, and still constitute a com-mon cause of vulnerability. During 2012-2018, buffer overruns were the source of 9.7% to 18.4% of CVEs re-ported in the NIST vulnerability database, constituting the leading single cause of CVEs.