Get started
Author

Krishna Kanth Nakka

Observed names: Krishna K. Nakka, Krishna K. Nakka (3956501), Krishna Nakka, NAKKA, KRISHNA KANTH, Nakka, Krishna K., Nakka, Krishna Kanth
ORCID: 0000-0002-2381-6593
Observed ORCID: 0000-0002-2381-6593
OpenAlex ID: A5008425976
Detecting the Unexpected via Image Resynthesis
2019 · Krzysztof Lis, Krishna Kanth Nakka, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 181
PDF
Learning Transferable Adversarial Perturbations
2021 · Krishna Kanth Nakka, Mathieu Salzmann · neural information processing systems · 32
Indirect Local Attacks for Context-Aware Semantic Segmentation Networks
2020 · Krishna Kanth Nakka, Mathieu Salzmann · Lecture notes in computer science · 28
PDF
Deep Learning Based Fence Segmentation and Removal from an Image Using a Video Sequence
2016 · Sankaraganesh Jonna, Krishna K. Nakka, et al. · Lecture notes in computer science · 18
PDF
My camera can see through fences: A deep learning approach for image de-fencing
2015 · Sankaraganesh Jonna, Krishna K. Nakka, et al. · Asian Conference on Pattern Recognition · 16
PDF
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding
2024 · Krishna Nakka, Ahmed Frikha, et al. · Workshop on Privacy in Natural Language Processing (PrivateNLP) · 8
PDF
Deep Attentional Structured Representation Learning for Visual Recognition
2018 · Nakka, Krishna Kanth, Salzmann, Mathieu · arXiv (Cornell University) · 7
PDF
Universal, Transferable Adversarial Perturbations for Visual Object Trackers
2023 · Krishna Kanth Nakka, Mathieu Salzmann · Lecture notes in computer science · 6
Detection and removal of fence occlusions in an image using a video of the static/dynamic scene
2016 · Sankaraganesh Jonna, Krishna K. Nakka, et al. · Journal of the Optical Society of America A · 6
Towards Robust Fine-Grained Recognition by Maximal Separation of Discriminative Features
2021 · Krishna Kanth Nakka, Mathieu Salzmann · Lecture notes in computer science · 5
PDF
Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers
2020 · Nakka, Krishna Kanth, Salzmann, Mathieu · arXiv (Cornell University) · 5
PDF
3D-to-2D mapping for user interactive segmentation of human leg muscles from MRI data
2014 · Nilanjan Ray, Satarupa Mukherjee, et al. · IEEE Global Conference on Signal and Information Processing · 5
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
2025 · Ahmed Frikha, Muhammad Reza Ar Razi, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · 3
PDF
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
2025 · Ahmed Frikha, Nassim Walha, et al. · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · 3
Federated Hyperparameter Optimization through Reward-Based Strategies: Challenges and Insights
2024 · Krishna Kanth Nakka, Ahmed Frikha, et al. · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 3
Towards an Automated Image De-fencing Algorithm Using Sparsity
2016 · Jonna, Sankaraganesh, Nakka, Krishna K., et al. · arXiv (Cornell University) · 2
PDF
PII-Scope: A Comprehensive Study on Training Data PII Extraction Attacks in LLMs
2024 · Nakka, Krishna Kanth, Frikha, Ahmed, et al. · arXiv (Cornell University) · 1
PDF
PrivacyEvalClaw: A Tool-Augmented Deliberative Agent for Auditing Privacy Leakage in LLM Jailbreak Responses
2026 · Nakka, Krishna Kanth, Wang, Yujun, et al. · arXiv (Cornell University)
PDF
MammoClaw: Towards Skill-Evolving Agent Harness for Breast Cancer Mammography Analysis
2026 · Nakka, Krishna Kanth · arXiv (Cornell University)
PDF
From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning?
2026 · Nakka, Krishna Kanth, Nakka, Vedasri · arXiv (Cornell University)
PDF
PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
2026 · Krishna Kanth Nakka, Xue Jiang, et al. · Workshop on Trustworthy NLP (TrustNLP)
PDF
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
2025 · Association for Computational Linguistics 2025, Frikha, Ahmed, et al. · Underline Science Inc.
PII-Scope: A Comprehensive Study on Training Data Privacy Leakage in Pretrained LLMs
2025 · Association for Computational Linguistics 2025, Frikha, Ahmed, et al. · Underline Science Inc.
Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
2025 · Krishna Kanth Nakka · Research Square
PDF
Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
2025 · Krishna Kanth Nakka · Lecture notes in computer science
Works count: 47
Citation count: 330
H-index: 7
I10-index: 5
Year
Topic
Type