Samyak Jain

Cited by

	All	Since 2019
Citations	185	185
h-index	5	5
i10-index	5	5

120

20212022202320241 19 45 114

Public access

View all

4 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Sravanti AddepalliPhD Student, Indian Institute of Science, BangaloreVerified email at iisc.ac.in
R. Venkatesh BabuCDS, Indian Institute of Science, Bangalore, IndiaVerified email at iisc.ac.in
Gaurang SriramananPhD Student, University of Maryland, College ParkVerified email at umd.edu
Ekdeep Singh LubanaHarvard / NTTVerified email at fas.harvard.edu
Priyam DeyPhD Student, Indian Institute of Science, BangaloreVerified email at iisc.ac.in
Hidenori TanakaGroup Leader, CBS-NTT Physics of Intelligence Program, Harvard UniversityVerified email at fas.harvard.edu
David Scott KruegerUniversity Assistant Professor, University of CambridgeVerified email at cam.ac.uk
Robert KirkResearch Scientist, UK AI Safety InstituteVerified email at dsit.gov.uk
Tim RocktäschelDirector and Open-Endedness Team Lead at Google DeepMind, Professor of AI at UCL, Fellow ELLISVerified email at cs.ucl.ac.uk
Edward GrefenstetteDirector of Research, Google DeepMind | Honorary Professor, UCLVerified email at google.com
Puneet K. DokaniaUniversity of Oxford | Five AIVerified email at robots.ox.ac.uk
Philip TorrProfessor, University of OxfordVerified email at eng.ox.ac.uk
Amartya SanyalUniversity of CopenhagenVerified email at di.ku.dk
Pratik ChattopadhyayAssistant Professor at Indian Institute of Technology (Banaras Hindu University), VaranasiVerified email at iitbhu.ac.in

Samyak Jain

Research Fellow at Microsoft Research

Verified email at itbhu.ac.in - Homepage

AI Safety Mechanistic Interpretability Adversarial Robustness


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Efficient and effective augmentation strategy for adversarial training S Addepalli, S Jain, RV Babu Advances in Neural Information Processing Systems 35, 1488-1501, 2022	56	2022
Scaling adversarial training to large perturbation bounds S Addepalli, S Jain, G Sriramanan, R Venkatesh Babu European Conference on Computer Vision, 301-316, 2022	51*	2022
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks S Jain, R Kirk, ES Lubana*, RP Dick, H Tanaka, E Grefenstette, ... International Conference on Learning Representations (ICLR), 2024, 2023	40	2023
Dart: Diversify-aggregate-repeat training improves generalization of neural networks S Jain, S Addepalli, PK Sahu, P Dey, RV Babu Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023	22	2023
Boosting adversarial robustness using feature level stochastic smoothing S Addepalli, S Jain, G Sriramanan*, RV Babu Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021	10	2021
What makes and breaks safety fine-tuning? a mechanistic study S Jain, ES Lubana, K Oksuz, T Joy, PHS Torr, A Sanyal, PK Dokania Advances in Neural Information Processing Systems (NeurIPS), 2024, 2024	4	2024
Towards Understanding and Improving Adversarial Robustness of Vision Transformers S Jain, T Dutta Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024	2	2024
Understanding and Improving Adversarial Robustness of Deep Neural Networks S Jain Indian Institute of Technology (BHU) Varanasi, 2023		2023
Supplementary: Towards Understanding and Improving Adversarial Robustness of Vision Transformers S Jain, T Dutta
Supplementary: DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks S Jain, S Addepalli, PK Sahu, P Dey, RV Babu
Supplementary Material: Towards Achieving Adversarial Robustness Beyond Perceptual Limits S Addepalli, S Jain, G Sriramanan, S Khare, RV Babu
Supplementary Material: Scaling Adversarial Training to Large Perturbation Bounds S Addepalli, S Jain, G Sriramanan, RV Babu
Supplementary Material: Boosting Adversarial Robustness using Feature Level Stochastic Smoothing S Addepalli, S Jain, G Sriramanan, RV Babu

The system can't perform the operation now. Try again later.

Articles 1–13

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors