10 papers
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…
Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models
Chashi Mahiul Islam, Alan Villarreal, Mao Nishino +2
As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical instability has emerged as a critical reliability…
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-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…
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…
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…
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…
DeepSeek on a Trip: Inducing Targeted Visual Hallucinations via Representation Vulnerabilities
Chashi Mahiul Islam, Samuel Jacob Chacko, Preston Horne +1
Multimodal Large Language Models (MLLMs) represent the cutting edge of AI technology, with DeepSeek models emerging as a leading open-source alternative offering competitive perfor…
Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers
Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino +1
While transformer-based models dominate NLP and vision applications, their underlying mechanisms to map the input space to the label space semantically are not well understood. In…
Adversarial Attacks on Large Language Models Using Regularized Relaxation
Samuel Jacob Chacko, Sajib Biswas, Chashi Mahiul Islam +2
As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significan…