activity
20242026
collaborators

9 papers

cs.CR2026

Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust

Vishnu Asutosh Dasu, Monika Santra, Md Rafi Ur Rashid +3

Extended Berkeley Packet Filter (eBPF) programs are kernel extensions used for networking, observability, and security enforcement in the Linux kernel. The in-kernel eBPF verifier…

cs.LG2026

Impact of Data Duplication on Deep Neural Network-Based Image Classifiers: Robust vs. Standard Models

Alireza Aghabagherloo, Aydin Abadi, Sumanta Sarkar +2

The accuracy and robustness of machine learning models against adversarial attacks are significantly influenced by factors such as training data quality, model architecture, the tr…

cs.CV2026

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

Md Rafi Ur Rashid, MD Sadik Hossain Shanto, Vishnu Asutosh Dasu +1

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demo…

cs.SE2026

iResolveX: Multi-Layered Indirect Call Resolution via Static Reasoning and Learning-Augmented Refinement

Monika Santra, Bokai Zhang, Mark Lim +3

Indirect call resolution remains a key challenge in reverse engineering and control-flow graph recovery, especially for stripped or optimized binaries. Static analysis is sound but…

cs.CR2025

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering

Md Rafi Ur Rashid, Vishnu Asutosh Dasu, Kang Gu +2

Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These a…

cs.AI2025

Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing

Vishnu Asutosh Dasu, Md Rafi ur Rashid, Vipul Gupta +2

This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitiv…