no code implementations • 19 Jul 2023 • Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov, Kristian Georgiev, Hadi Salman, Andrew Ilyas, Aleksander Madry
In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation.
1 code implementation • 13 Feb 2023 • Hadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry
We present an approach to mitigating the risks of malicious image editing posed by large diffusion models.
1 code implementation • CVPR 2023 • Saachi Jain, Hadi Salman, Alaa Khaddaj, Eric Wong, Sung Min Park, Aleksander Madry
It is commonly believed that in transfer learning including more pre-training data translates into better performance.
no code implementations • WS 2019 • Alaa Khaddaj, Hazem Hajj, Wassim El-Hajj
While transfer learning for text has been very active in the English language, progress in Arabic has been slow, including the use of Domain Adaptation (DA).
2 code implementations • 25 May 2019 • Ramy Baly, Alaa Khaddaj, Hazem Hajj, Wassim El-Hajj, Khaled Bashir Shaban
Sentiment analysis is a highly subjective and challenging task.
no code implementations • SEMEVAL 2018 • Gilbert Badaro, Obeida El Jundi, Alaa Khaddaj, Alaa Maarouf, Raslan Kain, Hazem Hajj, Wassim El-Hajj
Moreover, several features were evaluated along with different classification and regression techniques.