Currently investigating multiple methods and improvements involving adversarial attacks in the text domain as well as defenses against them.
Researching bias mitigation and detection. Furthermore, currently aiming to establish a baseline of human bias to compare AI against.
Previous research started down this path and I am open to collaboration for privacy in text and other media.
I am also interested in collaborating in other text research which focuses on censorship and subverting it.
I am very open to other collaboration in the NLP domain as well especially focusing on various social media platforms.
Feel free to send me an email for any meeting or discussion.