activity
20242026
collaborators

15 papers

cs.CR2026

Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

Faisal Haque Bappy, Tahrim Hossain, Tarannum Shaila Zaman +3

Multi-agent LLM pipelines orchestrate multiple specialized language model agents into structured workflows where intermediate outputs are passed across agents to solve complex task…

cs.CR2026

Rollback-Free Cross-Chain Atomicity Through Forward-Only Correction

Tahrim Hossain, Faisal Haque Bappy, Tarannum Shaila Zaman +1

Blockchain platforms have grown into an ecosystem of independent networks, and a growing class of applications now requires smart contracts on separate chains to act as one. Such o…

cs.CR2026

Towards Secure and Trustworthy DAOs for Cross-Chain Governance

Faisal Haque Bappy, Tahrim Hossain, Tarannum Shaila Zaman +1

Cross-chain DAOs face unique security challenges that go beyond traditional single-chain vulnerabilities. This paper identifies and categorizes four critical attack vectors in cros…

cs.SE2026

DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code

Nabiha Parvez, Tanvin Sarkar Pallab, Mia Mohammad Imran +1

Debugging consumes a substantial portion of the software development lifecycle, yet the effectiveness of Large Language Models(LLMs) in this task is not well understood. Competitiv…

cs.SE2026

OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering

Mia Mohammad Imran, Tarannum Shaila Zaman

Large Language Models (LLMs) are increasingly used in empirical software engineering (ESE) to automate or assist annotation tasks such as labeling commits, issues, and qualitative…

cs.SE2026

SysPro: Reproducing System-level Concurrency Bugs from Bug Reports

Tarannum Shaila Zaman, Zhihui Yan, Chen Wang +3

Reproducing system-level concurrency bugs requires both input data and the precise interleaving order of system calls. This process is challenging because such bugs are non-determi…