Specialization

Adversarial Machine Learning, Deep Learning, and Natural Language Processing

Email

ashish.bajaj@thapar.edu

Education
1.    PhD in Information Technology from Delhi Technological University, Delhi.
•    Title – “Design of Framework for Adversarial Attacks & Defences in Classification Models”.  
2.    M. Tech. in Information Technology from Guru Gobind Singh Indraprastha University, Delhi.
3.    B. Tech. in Computer Science and Engineering from Guru Gobind Singh Indraprastha University, Delhi. 
4.    Schooling from Sri Guru Nanak Public School, Delhi.

Trainings
1.    Certificates in several QIPs/FDPs from organizations like AICTE, NIT Delhi, and IITs.
2.    Certificate course in Cyber Security (CEH) at Nucleus Computers Ltd.
3.    Certificate course in (JAVA, JDBC, AWT swing) at Vtech Academy of Computers.
4.    Certificate in graphic designing with PUMA sports India pvt ltd.

Experience
1.    Assistant Professor, Computer Science and Engineering Department, Thapar University Patiala, India (August 2024 - present)
2.    Teaching Assistantship, Department of Information Technology, Delhi Technological University formerly (DCE), Delhi, India (August 2021 – July 2024)

Journal publications
1.    A. Bajaj and D. K. Vishwakarma, “HOMOCHAR: A novel adversarial attack framework for exposing the vulnerability of text based neural sentiment classifiers,” Engineering Applications of Artificial Intelligence, vol. 126, Nov. 2023, doi: 10.1016/j.engappai.2023.106815. (Impact Factor-7.5, SCI Indexed)
2.    A. Bajaj and D. K. Vishwakarma, “A state-of-the-art review on adversarial machine learning in image classification,” Multimedia Tools & Applications, 2023, doi: 10.1007/s11042-023-15883-z. (Impact Factor-3.0, SCI Indexed)
3.    A. Bajaj and D. Kumar Vishwakarma, “Evading text-based emotion detection mechanism via adversarial attacks,” Neurocomputing, vol. 558, p. 126787, Nov. 2023, doi: 10.1016/j.neucom.2023.126787. (Impact Factor-5.5, SCI Indexed)
4.    A. Bajaj and D. K. Vishwakarma, “Non-Alpha-Num: a novel architecture for generating adversarial examples for bypassing NLP-based clickbait detection mechanisms,” International Journal of Information Security, 2024, doi: 10.1007/s10207-024-00861-9. (Impact Factor-2.4, SCI Indexed)
5.    A. Bajaj and D. K. Vishwakarma, " Bypassing Neural Text Classification Mechanism by Perturbing Inflectional Morphology of Words.” Accepted in Neural Networks, August 2024. (Impact Factor-6.0, SCI Indexed)
6.    S. Aggarwal, A. Bajaj and D. K. Vishwakarma, " Is your Adversarial Example Grammatically Correct? A Novel Textual Adversarial Attack Framework for Linguistic Acceptability” Accepted in International Journal of Information Security, June 2024. (Impact Factor-2.4, SCI Indexed)

Conference publications
1.    A. Bajaj and D. K. Vishwakarma, “ARG-Net: Adversarial Robust Generalized Network to Defend Against Word-Level Textual Adversarial Attacks,” in 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), Institute of Electrical and Electronics Engineers (IEEE), Jun. 2024, pp. 1–7. doi: 10.1109/i2ct61223.2024.10543623.
2.    A. Bajaj and D. K. Vishwakarma, “Deceiving Deep Learning-based Fraud SMS Detection Models through Adversarial Attacks,” in Proceedings - 17th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 327–332. doi: 10.1109/SITIS61268.2023.00059.
3.    A. Bajaj and D. K. Vishwakarma, “Bypassing Deep Learning based Sentiment Analysis from Business Reviews,” in 2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN), IEEE, May 2023, pp. 1–6. doi: 10.1109/ViTECoN58111.2023.10157098.
4.    A. Bajaj and D. K. Vishwakarma, “Exposing the Vulnerabilities of Deep Learning Models in News Classification,” in 2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT), IEEE, Feb. 2023, pp. 1–5. doi: 10.1109/ICITIIT57246.2023.10068577.
5.    R. Sharma, A. Ghosh, A. Bajaj, and D. K. Vishwakarma, “BEACOMP: A Novel Textual Adversarial Attack Architecture for Unveiling the Fragility of Neural Text Classifiers,” in 4 2nd International Conference on Advancement in Computation & Computer Technologies (InCACCT), Institute of Electrical and Electronics Engineers (IEEE), Jun. 2024, pp. 161–166. doi: 10.1109/incacct61598.2024.10550990.

Peer reviewer for Journals
●    Engineering Applications of Artificial Intelligence, Elsevier
●    Neurocomputing, Elsevier
●    International Journal of Information Security, Springer
●    IEIE Transactions on Smart Processing and Computing

Honours and Achievements
●    Qualified National Eligibility Test (UGC-NET) for Assistant Professorship in December 2020.