Krishna Kanth Nakka

29 papers A* 2A 2Journal 17Unranked 8
YearRankTypeTitle / Venue / Authors
2026 J jnl
From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning?
CoRR
Krishna Kanth Nakka, Vedasri Nakka
2025 — conf
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization.
IJCNLP-AACL (long papers)
Ahmed Frikha, Nassim Walha, Krishna Kanth Nakka, Ricardo Mendes, Xue Jiang, Xuebing Zhou
2025 — conf
Mammo-SAE : Interpreting Breast Cancer Concept Learning with Sparse Autoencoders.
Deep-Breath@MICCAI
Krishna Kanth Nakka
2025 J jnl
Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders.
CoRR
Krishna Kanth Nakka
2025 A conf
NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability.
WACV
Krishna Kanth Nakka, Alexandre Alahi
2025 J jnl
NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability.
CoRR
Krishna Kanth Nakka, Alexandre Alahi
2025 J jnl
PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage.
CoRR
Krishna Kanth Nakka, Xue Jiang, Xuebing Zhou
2025 — conf
PII-Scope: A Comprehensive Study on Training Data Privacy Leakage in Pretrained LLMs.
IJCNLP-AACL (long papers)
Krishna Kanth Nakka, Ahmed Frikha, Ricardo Mendes, Xue Jiang, Xuebing Zhou
2025 J jnl
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders.
CoRR
Ahmed Frikha, Muhammad Reza Ar Razi, Krishna Kanth Nakka, Ricardo Mendes, Xue Jiang, Xuebing Zhou
2024 — conf
Federated Hyperparameter Optimization through Reward-Based Strategies: Challenges and Insights.
CVPR Workshops
Krishna Kanth Nakka, Ahmed Frikha, Ricardo Mendes, Xue Jiang, Xuebing Zhou
2024 J jnl
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization.
CoRR
Ahmed Frikha, Nassim Walha, Krishna Kanth Nakka, Ricardo Mendes, Xue Jiang, Xuebing Zhou
2024 J jnl
ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets.
CoRR
Ahmed Frikha, Nassim Walha, Ricardo Mendes, Krishna Kanth Nakka, Xue Jiang, Xuebing Zhou
2024 J jnl
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding.
CoRR
Krishna Kanth Nakka, Ahmed Frikha, Ricardo Mendes, Xue Jiang, Xuebing Zhou
2024 J jnl
PII-Scope: A Benchmark for Training Data PII Leakage Assessment in LLMs.
CoRR
Krishna Kanth Nakka, Ahmed Frikha, Ricardo Mendes, Xue Jiang, Xuebing Zhou
2023 J jnl
Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation.
CoRR
Krishna Kanth Nakka, Mathieu Salzmann
2022 — conf
Universal, Transferable Adversarial Perturbations for Visual Object Trackers.
ECCV Workshops (1)
Krishna Kanth Nakka, Mathieu Salzmann
2021 A* conf
Learning Transferable Adversarial Perturbations.
NeurIPS
Krishna Kanth Nakka, Mathieu Salzmann
2020 — conf
Indirect Local Attacks for Context-Aware Semantic Segmentation Networks.
ECCV (5)
Krishna Kanth Nakka, Mathieu Salzmann
2020 J jnl
Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers.
CoRR
Krishna Kanth Nakka, Mathieu Salzmann
2020 — conf
Towards Robust Fine-Grained Recognition by Maximal Separation of Discriminative Features.
ACCV (6)
Krishna Kanth Nakka, Mathieu Salzmann
2020 J jnl
Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features.
CoRR
Krishna Kanth Nakka, Mathieu Salzmann
2019 A* conf
Detecting the Unexpected via Image Resynthesis.
ICCV
Krzysztof Lis, Krishna Kanth Nakka, Pascal Fua, Mathieu Salzmann
2019 J jnl
Indirect Local Attacks for Context-aware Semantic Segmentation Networks.
CoRR
Krishna Kanth Nakka, Mathieu Salzmann
2019 J jnl
Interpretable BoW Networks for Adversarial Example Detection.
CoRR
Krishna Kanth Nakka, Mathieu Salzmann
2018 A conf
Deep Attentional Structured Representation Learning for Visual Recognition.
BMVC
Krishna Kanth Nakka, Mathieu Salzmann
2018 J jnl
Deep Attentional Structured Representation Learning for Visual Recognition.
CoRR
Krishna Kanth Nakka, Mathieu Salzmann
2018 J jnl
My camera can see through fences: A deep learning approach for image de-fencing.
CoRR
Sankaraganesh Jonna, Krishna Kanth Nakka, Rajiv R. Sahay
2016 J jnl
Automatic Image De-fencing System.
CoRR
Krishna Kanth Nakka
2014 — conf
3D-to-2D mapping for user interactive segmentation of human leg muscles from MRI data.
GlobalSIP
Nilanjan Ray, Satarupa Mukherjee, Krishna Kanth Nakka, Scott T. Acton, Silvia S. Blanker