From the 1 of 22 linked papers with an AI index.
22 papers
When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech
Akif Islam, Raufun Nahar, Md. Ekramul Hamid
The paper investigates whether applying the SAM-Audio denoising front‑end improves zero‑shot transcription with OpenAI Whisper on noisy Bengali and English speech, and finds that d…
Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks
Mohd Ruhul Ameen, Akif Islam, Nadim Mahmud +1
Statistical watermarking is a common approach for verifying whether text was written by a language model. Most existing schemes assume autoregressive generation, where tokens are p…
QASecClaw: A Multi-Agent LLM Approach for False Positive Reduction in Static Application Security Testing
Mohd Ruhul Ameen, Md Takrim Ul Alam, Akif Islam
Static Application Security Testing tools help developers find security vulnerabilities before release, but they often produce many false positives. This increases manual review ef…
Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints
Md. Fahad Ullah Utsho, Mohd. Ruhul Ameen, Akif Islam +2
Large Language Models (LLMs) are increasingly described as possessing strong reasoning capabilities, supported by high performance on mathematical, logical, and planning benchmarks…
Beyond Ray-Casting: Evaluating Controller, Free-Hand, and Virtual-Touch Modalities for Immersive Text Entry
Md. Tanvir Hossain, Mohd Ruhul Ameen, Akif Islam +5
Efficient text entry remains a primary bottleneck preventing Virtual Reality (VR) from evolving into a viable productivity platform. To address this, we conducted an empirical comp…
Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems
Md Takrim Ul Alam, Akif Islam, Mohd Ruhul Ameen +2
Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subv…