Embedded Files
๐ฅธ= AIGC Detection ๐ฃ = Diffusion Model Research๐คก = Adversarial Machine Learning Research ๐๏ธ= Robustness Research ๐ง = Understanding Neural Network Researchย ๐ฎ= Driving Simulation Research ๐ค = IoT Research ๐ป = Cognitive Radio Researchย
(X) = Draft/Submission #3ย (J) = Journals #5ย (C) = Conference #5ย (W) = Workshopsย #3ย (T) = Technical Reports #4(DT) = Doctorate Thesis (PT) = Postgraduate Thesis (UT) = Undergraduate Thesis
(*) Equal Contribution
(X) = Draft/Submission #3ย (J) = Journals #5ย (C) = Conference #5ย (W) = Workshopsย #3ย (T) = Technical Reports #4(DT) = Doctorate Thesis (PT) = Postgraduate Thesis (UT) = Undergraduate Thesis
(*) Equal Contribution
In Draftsย
[๐คก๐ง ][X.3] Linking Robustness and Generalization: A k* Distribution Analysis of Concept Clustering in Latent Space for Vision Models
Shashank Kotyan, Pin-Yu Chen, and Danilo Vasconcellos Vargas(๐ Link to pre-print article)[๐คก๐ฃ][X.2] Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!
Shashank Kotyan*, Po-Yuan Mao*, Pin-Yu Chen, and Danilo Vasconcellos Vargas( ๐ Blog Post) (๐ Project Webpage) (๐ Link to pre-print article)[๐ฃ๐คก][X.1] Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Models
Po-Yuan Mao*, Shashank Kotyan*, Tham Yik Foong, and Danilo Vasconcellos Vargas(๐ Link to pre-print article)2025
[๐ง ๐คก๐๏ธ][DT] Understanding, Evaluating and Enhancing the Adversarial Robustness of Neural Networks: A multi-faceted study on Attacks, Latent Space and Architectures
Shashank Kotyanย[๐ฅธ๐ง ][W.3] Percept-Lens: A Large-Scale Benchmark for Generalization in AI-Generated Image Detection with Diverse Images and Generative Models
Shashank Kotyan, Yuki Imajuku, Makoto Shing, and Tarin ClanuwatPublished in 2025 at Second Workshop on Responsible Generative AI (ReGenAI 2025) at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)ย ย (๐Link to Sakana AI Blog) (๐ Link to Poster) (๐ข Link to Published Article)2024
T=3, J=2
[๐ง ][J.5] k* Distribution: Evaluating the Latent Space of Deep Neural Networks using Local Neighborhood Analysis
Shashank Kotyan*, Ueda Tatsuya*, Danilo Vasconcellos VargasPublished in IEEE Transactions on Neural Networks and Learning Systems(๐ฐ Nikkei Article JP) (๐ฐ University Press Release JP PDF) (๐ฐ University Press Release JP) (๐ฐ University Press Release EN PDF) (๐ฐ University Press Release EN)(๐ Link to Slides JP) (๐ Link to Slides EN)ย (๐ Project Webpage) (๐จโ๐ปLink to Code) (๐ Link to pre-print article) (๐ข Link to Published Article)[๐๏ธ๐คก][J.4] Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation
Shashank Kotyan, and Danilo Vasconcellos VargasPublished in Volume 565 of Neurocomputingย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย ย (๐ Link to pre-print article) (๐ข Link to Published Article)
[๐ง ๐ฃ][T.4] The Challenges of Image Generation Models in Generating Multi-Component Images
Tham Yik Foong, Shashank Kotyan, Po-Yuan Mao, and Danilo Vasconcellos Vargas(๐ Link to pre-print article)[๐๏ธ๐คก][T.3] Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning
Shashank Kotyan, and Danilo Vasconcellos Vargas(๐ Link to pre-print article)[๐๏ธ๐คก][T.2] Towards Improving Robustness Against Common Corruptions using Mixture of Class Specific Experts
Shashank Kotyan, and Danilo Vasconcellos Vargas(๐ Link to pre-print article)2023
T=1
[๐คก][T.1] A reading survey on adversarial machine learning: Adversarial attacks and their understanding
Shashank Kotyan(๐ Link to pre-print article)[๐ง ๐คก๐๏ธ][PT] Towards Developing Robust Neural Networks By Understanding Adversarial Attacks and Defences
Shashank Kotyanย2022
J=2
[๐คก๐ง ][J.3] Transferability of features for neural networks links to adversarial attacks and defences
Shashank Kotyan, Moe Matsuki, and Danilo Vasconcellos VargasPublished in PLOS ONE(๐ฐ University Press Release JP PDF) (๐ฐ University Press Release JP) (๐ฐ University Press Release EN PDF) (๐ฐ University Press Release EN)(๐จโ๐ปLink to Code) (๐ Link to pre-print article) (๐ข Link to Published Article)[๐คก][J.2] Adversarial Robustness Assessment: Why Both L0 And Lโ Attacks Are Necessary
Shashank Kotyan , Danilo Vasconcellos VargasPublished in PLOS ONE(๐จโ๐ปLink to Code) (๐ Link to pre-print article) (๐ข Link to Published Article)ย2021
W=1
[๐คก๐ง ][W.2] Deep Neural Network Loses Attention To Adversarial Images
Shashank Kotyan, and Danilo Vasconcellos VargasPublished in 2021 at Workshop on Artificial Intelligence Safety (AISafety 2021) at the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021)(๐ฃ Link to Presentation) (๐ Link to Slides)ย (๐ Link to pre-print article) (๐ข Link to Published Article)2020
C=2, W=1
[๐๏ธ๐คก][W.1] Evolving Robust Neural Architectures To Defend From Adversarial Attack
Shashank Kotyan, and Danilo Vasconcellos VargasPublished in 2020 at Workshop on Artificial Intelligence Safety (AISafety 2020) at the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI 2020)ย (๐ฃ Link to Presentation) (๐ Link to Slides)ย (๐จโ๐ปLink to Code) (๐ Link to pre-print article) (๐ข Link to Published Article)[๐๏ธ๐คก][C.5] Is Neural Architecture Search A Way Forward To Develop Robust Neural Networks?
Shashank Kotyan, and Danilo Vasconcellos VargasPublished in 2020 at the 34th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI 2020)(๐จโ๐ปLink to Code) (๐ข Link to Published Article)[๐๏ธ๐คก][C.4] Towards Evolving Robust Neural Architectures To Defend From Adversarial Attacks
Shashank Kotyan, and Danilo Vasconcellos VargasPublished in 2020 at the 21st Genetic and Evolutionary Computation Conference Companion (GECCO 2020).(๐จโ๐ปLink to Code) (๐ข Link to Published Article)2019
C=1
[๐ง ๐คก๐๏ธ][UT] Understanding Vulnerabilities Of Deep Neural Networks To Evolve Robust Neural Architectures
Shashank Kotyanย[๐ฎ][C.3] Self Training Autonomous Driving Agentย
Shashank Kotyan, Danilo Vasconcellos Vargas,ย and Venkanna Udutalapallyย Published in 2019 at the 58th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE 2019)(๐ Link to pre-print article) (๐ข Link to Published Article)ย ย2018
C=2, J=1
[๐ค][C.2] Drishtikon: An Advanced Navigation System For Visually Impaired People
Shashank Kotyan, Venkanna Udutalapally, Nishant Kumar, and Pankaj Kumar SahuPublished in 2018 at the 2nd Conference on Information and Communication Technology (CICT 2018)ย ย (๐ Link to pre-print article) (๐ข Link to Published Article)[๐ค][C.1] HAUAR: Home Automation Using Action Recognition
Shashank Kotyan, Nishant Kumar, Pankaj Kumar Sahu,ย and Venkanna UdutalapallyPublished in 2018 at the 2nd Conference on Information and Communication Technology (CICT 2018)ย (๐ Link to pre-print article) (๐ข Link to Published Article)[๐ป] [J.1] Analysis And Comparison Of Different Fuzzy Inference Systems Used In Decision Making For Secondary Users In Cognitive Radio Network
Shrivishal Tripathi, Ashish Upadhyay, Shashank Kotyan,ย and Sandeep YadavPublished in Volume 104, Issue 3 of Wireless Personal Communication(๐ Link to pre-print article) (๐ข Link to Published Article)"The road to wisdom? -- Well, it's plain and simple to express: Err and err and err again but less and less and less."
"The road to wisdom? -- Well, it's plain and simple to express: Err and err and err again but less and less and less."
-Piet Hein
-Piet Hein
Last Updated: July 2025
Page updated
Google Sites
Report abuse