CS 607: Topics in Computer Science (Directed Study)

Course Portfolio || Papers Write-Ups || Fall 2022

Saied Alshahrani, a PhD student in CS

Prof. Jeanna N. Matthews

#	Paper Title	Authors	Venue and Year	Write-Ups	Reading Date
1	Generating Natural Language Adversarial Examples	Alzantot et al.	EMNLP 2018		09/12/2022
2	Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers	Gao et al.	IEEE Symposiumon on Security and Privacy 2018		09/15/2022
3	HotFlip: White-Box Adversarial Examples for Text Classification	Ebrahimi et al.	ACL 2018		09/19/2022
4	Adversarial Examples for Natural Language Classification Problems	Kuleshov et al.	Rejected @ ICLR 2018 but good paper to read		09/21/2022
5	Pathologies of Neural Models Make Interpretation Difficult	Feng et al.	EMNLP 2018		10/26/2022
6	Certified Robustness to Adversarial Word Substitution	Jia et al.	EMNLP 2019		10/03/2022
7	Toward Mitigating Adversarial Texts	Alshemali and Kalita	International Journal of Computer Applications 2019		10/05/2022
8	Combating Adversarial Misspellings with Robust Word Recognition	Pruthi et al.	ACL 2019		10/10/2022
9	TextBugger: Generating Adversarial Text Against Real-world Applications	Li et al.	NDSS 2019		10/12/2022
10	Adversarial Examples in Arabic (Supplementary Material)	Alshemali and Kalita	CSCI 2019		10/17/2022
11	Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency	Ren et al.	ACL 2019		10/19/2022
12	BAE: BERT-based Adversarial Examples for Text Classification	Garg and Ramakrishnan	EMNLP 2020		10/24/2022
13	Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples	Cheng et al.	AAAI 2020		10/26/2022
14	Is Bert Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment	Jin et al.	AAAI 2020		11/02/2022
15	TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP	Morris et al.	EMNLP 2020		11/07/2022
16	BERT-ATTACK: Adversarial Attack Against BERT Using BERT	Li et al.	EMNLP 2020		11/09/2022
17	Beyond Accuracy: Behavioral Testing of NLP models with CheckList	Ribeiro et al.	ACL 2020		11/14/2022
18	Word-level Textual Adversarial Attacking as Combinatorial Optimization	Zang et al.	ACL 2020		11/17/2022
19	Character-level Adversarial Examples in Arabic	Alshemali and Kalita	ICMLA 2021		11/20/2022
20	Contextualized Perturbation for Textual Adversarial Attack	Li et al.	NAACL 2021		11/24/2022

#	Periodic/Semester Deliverables	Files	Publication Date
1	Progress Report of September 2022 [Report]		09/30/2022
2	Progress Report of October 2022 [Report]		10/31/2022
3	Progress Report of November 2022 [Report]		11/27/2022
6	Learning From Arabic Corpora But Not Always From Arabic Speakers: A Case Study of the Arabic Wikipedia Editions [Presentation]		12/07/2022
5	Learning From Arabic Corpora But Not Always From Arabic Speakers: A Case Study of the Arabic Wikipedia Editions* [Paper] *Accepted at the 7th Arabic Natural Language Processing Workshop (WANLP 2022), co-located with the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), December 7-8, 2022.		12/08/2022
4	Aladdin Genies: Arabic Adversarial Text Normalization Attacks [Project]		12/12/2022