activity
20242026
collaborators

9 papers

cs.AI2026

When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity

Samuel Jacob Chacko, James Hugglestone, Chashi Mahiul Islam +1

Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentag…

cs.CR2026

STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving

James Hugglestone, Samuel Jacob Chacko, Dawson Stoller +2

Large Language Models (LLMs) have demonstrated potential in code generation, yet they struggle with the multi-step, stateful reasoning required for offensive cybersecurity operatio…

cs.CY2025

CS-Guide: Leveraging LLMs and Student Reflections to Provide Frequent, Scalable Academic Monitoring Feedback to Computer Science Students

Samuel Jacob Chacko, An-I Andy Wang, Lara Perez-Felkner +3

Computer Science (CS) departments often serve large student populations, making timely academic monitoring and personalized feedback difficult. While the recommended counselor-to-s…

cs.CV2025

Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning

Chashi Mahiul Islam, Oteo Mamo, Samuel Jacob Chacko +2

Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations. To address this, we…

cs.LG2025

Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

Sajib Biswas, Mao Nishino, Samuel Jacob Chacko +1

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall su…

cs.LG2025

Adversarial Attack on Large Language Models using Exponentiated Gradient Descent

Sajib Biswas, Mao Nishino, Samuel Jacob Chacko +1

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are ali…