3 papers
cs.CR2026
On the Geometric Limits of Transformer Defenses against Obfuscation Attacks: Latent Embedding Collapse & Performance Robustness Gap
Becky Mashaido, Tapadhir Das
Prompt injection attacks pose significant risks to language model safety, yet existing defenses are typically evaluated using classification performance. We show that high detectio…
cs.LG2021
A Tale of Fairness Revisited: Beyond Adversarial Learning for Deep Neural Network Fairness
Becky Mashaido, Winston Moh Tangongho
Motivated by the need for fair algorithmic decision making in the age of automation and artificially-intelligent technology, this technical report provides a theoretical insight in…
cs.CV2021
Learning Grammar of Complex Activities via Deep Neural Networks
Becky Mashaido
Motivated by the growing amount of publicly available video data on online streaming services and an increased interest in applications that analyze continuous video streams such a…