45 citations · 90 across the 10 of their papers we have counts for
13 papers
Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners
Leo Y. Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen +1
Embodied vision-language models (VLMs) are increasingly deployed as high-level planners for robots because they generalize across diverse environments. However, this requires their…
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…
STARS: Synchronous Token Alignment for Robust Supervision in Large Language Models
Mohammad Atif Quamar, Mohammad Areeb, Mikhail Kuznetsov +2
Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over generation; however, they rely on mode…
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…
Enhancing LLM-based Autonomous Driving Agents to Mitigate Perception Attacks
Ruoyu Song, Muslum Ozgur Ozmen, Hyungsub Kim +2
There is a growing interest in integrating Large Language Models (LLMs) with autonomous driving (AD) systems. However, AD systems are vulnerable to attacks against their object det…
On the Safety Implications of Misordered Events and Commands in IoT Systems
Furkan Goksel, Muslum Ozgur Ozmen, Michael Reeves +2
IoT devices, equipped with embedded actuators and sensors, provide custom automation in the form of IoT apps. IoT apps subscribe to events and upon receipt, transmit actuation comm…
Compatible Certificateless and Identity-Based Cryptosystems for Heterogeneous IoT
Rouzbeh Behnia, Attila A. Yavuz, Muslum Ozgur Ozmen +1
Certificates ensure the authenticity of users' public keys, however their overhead (e.g., certificate chains) might be too costly for some IoT systems like aerial drones. Certifica…
Discovering IoT Physical Channel Vulnerabilities
Muslum Ozgur Ozmen, Xuansong Li, Andrew Chu +3
Smart homes contain diverse sensors and actuators controlled by IoT apps that provide custom automation. Prior works showed that an adversary could exploit physical interaction vul…
Ultra Lightweight Multiple-time Digital Signature for the Internet of Things Devices
Attila A. Yavuz, Muslum Ozgur Ozmen
Digital signatures are basic cryptographic tools to provide authentication and integrity in the emerging ubiquitous systems in which resource-constrained devices are expected to op…
IoD-Crypt: A Lightweight Cryptographic Framework for Internet of Drones
Muslum Ozgur Ozmen, Rouzbeh Behnia, Attila A. Yavuz
Internet of Drones (IoD) is expected to play a central role in many civilian and military applications, that require sensitive and mission-critical information to be processed. It…
Dronecrypt - An Efficient Cryptographic Framework for Small Aerial Drones
Muslum Ozgur Ozmen, Attila A. Yavuz
Aerial drones are becoming an integral part of application domains including but not limited to, military operations, package delivery, construction, monitoring and search/rescue o…
Energy-Aware Digital Signatures for Embedded Medical Devices
Muslum Ozgur Ozmen, Attila A. Yavuz, Rouzbeh Behnia
Authentication is vital for the Internet of Things (IoT) applications involving sensitive data (e.g., medical and financial systems). Digital signatures offer scalable authenticati…
ARIS: Authentication for Real-Time IoT Systems
Rouzbeh Behnia, Muslum Ozgur Ozmen, Attila A. Yavuz
Efficient authentication is vital for IoT applications with stringent minimum-delay requirements (e.g., energy delivery systems). This requirement becomes even more crucial when th…