7 citations · 13 across the 18 of their papers we have counts for
21 papers
MammoClaw: Towards Skill-Evolving Agent Harness for Breast Cancer Mammography Analysis
Krishna Kanth Nakka
In this work, we explore MammoClaw, a training-free agent framework that leverages frozen MLLMs for mammography analysis. To support agentic investigation, we equip the agent with…
From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning?
Krishna Kanth Nakka, Vedasri Nakka
Cyclists often encounter safety-critical situations in urban traffic, highlighting the need for assistive systems that support safe and informed decision-making. Recently, vision-l…
NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
Krishna Kanth Nakka, Alexandre Alahi
The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single m…
PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
Krishna Kanth Nakka, Xue Jiang, Dmitrii Usynin +1
This paper investigates privacy jailbreaking in LLMs via steering, focusing on whether manipulating activations can bypass LLM alignment and alter response behaviors to privacy rel…
Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
Krishna Kanth Nakka
Interpretability is critical in high-stakes domains such as medical imaging, where understanding model decisions is essential for clinical adoption. In this work, we introduce Spar…
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
Ahmed Frikha, Muhammad Reza Ar Razi, Krishna Kanth Nakka +3
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally I…
PII-Scope: A Comprehensive Study on Training Data PII Extraction Attacks in LLMs
Krishna Kanth Nakka, Ahmed Frikha, Ricardo Mendes +2
In this work, we introduce PII-Scope, a comprehensive benchmark designed to evaluate state-of-the-art methodologies for PII extraction attacks targeting LLMs across diverse threat…
ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
Ahmed Frikha, Nassim Walha, Ricardo Mendes +3
This work addresses the timely yet underexplored problem of performing inference and finetuning of a proprietary LLM owned by a model provider entity on the confidential/private da…
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
Ahmed Frikha, Nassim Walha, Krishna Kanth Nakka +3
In this work, we address the problem of text anonymization where the goal is to prevent adversaries from correctly inferring private attributes of the author, while keeping the tex…
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding
Krishna Kanth Nakka, Ahmed Frikha, Ricardo Mendes +2
The latest and most impactful advances in large models stem from their increased size. Unfortunately, this translates into an improved memorization capacity, raising data privacy c…
Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation
Krishna Kanth Nakka, Mathieu Salzmann
As 3D human pose estimation can now be achieved with very high accuracy in the supervised learning scenario, tackling the case where 3D pose annotations are not available has recei…
Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers
Krishna Kanth Nakka, Mathieu Salzmann
In recent years, the trackers based on Siamese networks have emerged as highly effective and efficient for visual object tracking (VOT). While these methods were shown to be vulner…
Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features
Krishna Kanth Nakka, Mathieu Salzmann
Adversarial attacks have been widely studied for general classification tasks, but remain unexplored in the context of fine-grained recognition, where the inter-class similarities…
Indirect Local Attacks for Context-aware Semantic Segmentation Networks
Krishna Kanth Nakka, Mathieu Salzmann
Recently, deep networks have achieved impressive semantic segmentation performance, in particular thanks to their use of larger contextual information. In this paper, we show that…
Detecting the Unexpected via Image Resynthesis
Krzysztof Lis, Krishna Nakka, Pascal Fua +1
Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we ta…
Interpretable BoW Networks for Adversarial Example Detection
Krishna Kanth Nakka, Mathieu Salzmann
The standard approach to providing interpretability to deep convolutional neural networks (CNNs) consists of visualizing either their feature maps, or the image regions that contri…
My camera can see through fences: A deep learning approach for image de-fencing
Sankaraganesh Jonna, Krishna Kanth Nakka, Rajiv R. Sahay
In recent times, the availability of inexpensive image capturing devices such as smartphones/tablets has led to an exponential increase in the number of images/videos captured. How…
Deep Attentional Structured Representation Learning for Visual Recognition
Krishna Kanth Nakka, Mathieu Salzmann
Structured representations, such as Bags of Words, VLAD and Fisher Vectors, have proven highly effective to tackle complex visual recognition tasks. As such, they have recently bee…
Towards an Automated Image De-fencing Algorithm Using Sparsity
Sankaraganesh Jonna, Krishna K. Nakka, Rajiv R. Sahay
Conventional approaches to image de-fencing suffer from non-robust fence detection and are limited to processing images of static scenes. In this position paper, we propose an auto…
Automatic Image De-fencing System
Krishna Kanth Nakka
Tourists and Wild-life photographers are often hindered in capturing their cherished images or videos by a fence that limits accessibility to the scene of interest. The situation h…
Deep learning based fence segmentation and removal from an image using a video sequence
Sankaraganesh Jonna, Krishna K. Nakka, Rajiv R. Sahay
Conventional approaches to image de-fencing use multiple adjacent frames for segmentation of fences in the reference image and are limited to restoring images of static scenes only…