6 papers
Follow My Eyes: Backdoor Attacks on Goal-Directed Scanpath Prediction
Diana Romero, Mutahar Ali, Momin Ahmad Khan +3
Scanpath prediction models forecast the sequence of fixations a person makes while searching a scene, and increasingly serve as the upstream perception layer for foveated rendering…
SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
Momin Ahmad Khan, Yasra Chandio, Fatima Muhammad Anwar
Federated Prompt Learning has emerged as a communication-efficient and privacy-preserving paradigm for adapting large vision-language models like CLIP across decentralized clients.…
Decoding FL Defenses: Systemization, Pitfalls, and Remedies
Momin Ahmad Khan, Virat Shejwalkar, Yasra Chandio +2
While the community has designed various defenses to counter the threat of poisoning attacks in Federated Learning (FL), there are no guidelines for evaluating these defenses. Thes…
HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
Momin Ahmad Khan, Yasra Chandio, Fatima Muhammad Anwar
Data heterogeneity among Federated Learning (FL) users poses a significant challenge, resulting in reduced global model performance. The community has designed various techniques t…
A Neurosymbolic Approach to Adaptive Feature Extraction in SLAM
Yasra Chandio, Momin A. Khan, Khotso Selialia +3
Autonomous robots, autonomous vehicles, and humans wearing mixed-reality headsets require accurate and reliable tracking services for safety-critical applications in dynamically ch…
Security Analysis of SplitFed Learning
Momin Ahmad Khan, Virat Shejwalkar, Amir Houmansadr +1
Split Learning (SL) and Federated Learning (FL) are two prominent distributed collaborative learning techniques that maintain data privacy by allowing clients to never share their…