DS
Across 1 conversation, Dawn Song ranges across blockchain, differential privacy, human factors in security. Adversarial machine learning can manipulate input data to mislead systems, posing risks at both inference and training stages. Social engineering attacks are increasingly targeting human vulnerabilities, with AI tools potentially aiding defense.
Synthesized by TLexDR from 1 conversation. AI-generated. Report an inaccuracy
The idea map
Dawn's intellectual territory
Click a star to read the quotes and jump into the episode.
For the specialist
previewAdversarial attacks can occur at both inference and training stages, highlighting the need for robust defenses against data poisoning.
#95Dawn Song: Adversarial Machine Learning and Computer Security
Blockchain's consensus mechanisms provide security but require additional privacy solutions due to their transparent nature.
#95Dawn Song: Adversarial Machine Learning and Computer Security
Program synthesis is advancing with applications like translating natural language into SQL, showcasing its potential in AI development.
#95Dawn Song: Adversarial Machine Learning and Computer Security
The appearance
Every conversation, in order
Reading list
What they pointed you toward
papers
Robust Physical World Attacks on Deep Learning Visual Classification
by 2018 paper
Every idea, by region