Zobrazeno 1 - 10
of 272
pro vyhledávání: '"Çelik Z"'
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 detection and tracking (ODT) functions. Unfortunately, our evaluation of
Externí odkaz:
http://arxiv.org/abs/2409.14488
Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such alignment can be
Externí odkaz:
http://arxiv.org/abs/2404.06407
Autor:
Goues, Claire Le, Elbaum, Sebastian, Anthony, David, Celik, Z. Berkay, Castillo-Effen, Mauricio, Correll, Nikolaus, Jamshidi, Pooyan, Quigley, Morgan, Tabor, Trenton, Zhu, Qi
Robots are experiencing a revolution as they permeate many aspects of our daily lives, from performing house maintenance to infrastructure inspection, from efficiently warehousing goods to autonomous vehicles, and more. This technical progress and it
Externí odkaz:
http://arxiv.org/abs/2401.12317
Users seek security & privacy (S&P) advice from online resources, including trusted websites and content-sharing platforms. These resources help users understand S&P technologies and tools and suggest actionable strategies. Large Language Models (LLM
Externí odkaz:
http://arxiv.org/abs/2310.02431
In Federated Learning (FL), the clients learn a single global model (FedAvg) through a central aggregator. In this setting, the non-IID distribution of the data across clients restricts the global FL model from delivering good performance on the loca
Externí odkaz:
http://arxiv.org/abs/2107.13173
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 commands which trigger a set of actuators. Events and actuation commands f
Externí odkaz:
http://arxiv.org/abs/2105.00645
With smart devices being an essential part of our everyday lives, unsupervised access to the mobile sensors' data can result in a multitude of side-channel attacks. In this paper, we study potential data leaks from Apple Pencil (2nd generation) suppo
Externí odkaz:
http://arxiv.org/abs/2103.05840
Autor:
Ozmen, Muslum Ozgur, Li, Xuansong, Chu, Andrew, Celik, Z. Berkay, Hoxha, Bardh, Zhang, Xiangyu
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 vulnerabilities among apps and put the users and environment at risk, e.g
Externí odkaz:
http://arxiv.org/abs/2102.01812
EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target. However, it
Externí odkaz:
http://arxiv.org/abs/2009.10639
Autor:
Berges, Paul M., Shivakumar, Basavesh Ammanaghatta, Graziano, Timothy, Gerdes, Ryan, Celik, Z. Berkay
Traffic Collision Avoidance Systems (TCAS) are safety-critical systems required on most commercial aircrafts in service today. However, TCAS was not designed to account for malicious actors. While in the past it may have been infeasible for an attack
Externí odkaz:
http://arxiv.org/abs/2006.14679