6 papers
A Self-Explainable Deep Architecture for Security Applications
Ananth Shreekumar, Jyun-Jhu Syu, Muslum Ozgur Ozmen +2
Deep learning models have become integral to security applications due to their ability to model complex relationships in data and detect sophisticated threats. However, their comp…
The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
Doguhan Yeke, Elif Su Temirel, Ananth Shreekumar +3
Vision-language models (VLMs) are used as high-level planners for embodied agents, translating natural language instructions and visual observations into action plans. While prior…
Stable GFlowNets with TV Monitoring and Probabilistic Guarantees
Zengxiang Lei, Ananth Shreekumar, Jonathan Rosenthal +6
Generative Flow Networks (GFlowNets) sample diverse structured objects in proportion to reward and have been applied to molecular discovery and biological-sequence design, where fi…
Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems
Edoardo Allegrini, Ananth Shreekumar, Z. Berkay Celik
Agentic AI systems, which leverage multiple autonomous agents and large language models (LLMs), are increasingly used to address complex, multi-step tasks. The safety, security, an…
Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models
Mohammad Atif Quamar, Mohammad Areeb, Nishant Sharma +5
LLM alignment remains a critical challenge. Inference-time methods provide a flexible alternative to fine-tuning, but their uniform computational effort often yields suboptimal ali…
Investigating the Impact of Dark Patterns on LLM-Based Web Agents
Devin Ersoy, Brandon Lee, Ananth Shreekumar +4
As users increasingly turn to large language model (LLM) based web agents to automate online tasks, agents may encounter dark patterns: deceptive user interface designs that manipu…