2 code implementations • 9 Apr 2024 • Hongyu Cai, Arjun Arunasalam, Leo Y. Lin, Antonio Bianchi, Z. Berkay Celik
We evaluate our metrics on a benchmark dataset produced from three malicious intent datasets and three jailbreak systems.
1 code implementation • 3 Oct 2023 • Yufan Chen, Arjun Arunasalam, Z. Berkay Celik
In this paper, we measure their ability to refute popular S&P misconceptions that the general public holds.
no code implementations • 28 Jul 2021 • Siddharth Divi, Yi-Shan Lin, Habiba Farrukh, Z. Berkay Celik
In this setting, the non-IID distribution of the data across clients restricts the global FL model from delivering good performance on the local data of each client.
no code implementations • 22 Sep 2020 • Yi-Shan Lin, Wen-Chuan Lee, Z. Berkay Celik
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.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 25 Jun 2020 • Paul M. Berges, Basavesh Ammanaghatta Shivakumar, Timothy Graziano, Ryan Gerdes, Z. Berkay Celik
Traffic Collision Avoidance Systems (TCAS) are safety-critical systems required on most commercial aircrafts in service today.
no code implementations • 24 Nov 2019 • Leonardo Babun, Z. Berkay Celik, Patrick McDaniel, A. Selcuk Uluagac
We designed and built IoTWatcH based on an IoT privacy survey that considers the privacy needs of IoT users.
no code implementations • 22 Nov 2019 • Amit Kumar Sikder, Leonardo Babun, Z. Berkay Celik, Abbas Acar, Hidayet Aksu, Patrick McDaniel, Engin Kirda, A. Selcuk Uluagac
Users can specify their desired access control settings using the interaction module which are translated into access control policies in the backend server.
Cryptography and Security
1 code implementation • 18 Sep 2018 • Z. Berkay Celik, Earlence Fernandes, Eric Pauley, Gang Tan, Patrick McDaniel
Based on a study of five IoT programming platforms, we identify the key insights resulting from works in both the program analysis and security communities and relate the efficacy of program-analysis techniques to security and privacy issues.
Cryptography and Security Programming Languages
1 code implementation • 22 Feb 2018 • Z. Berkay Celik, Leonardo Babun, Amit K. Sikder, Hidayet Aksu, Gang Tan, Patrick McDaniel, A. Selcuk Uluagac
Through this effort, we introduce a rigorously grounded framework for evaluating the use of sensitive information in IoT apps---and therein provide developers, markets, and consumers a means of identifying potential threats to security and privacy.
Cryptography and Security Programming Languages
no code implementations • 26 Nov 2016 • Z. Berkay Celik, David Lopez-Paz, Patrick McDaniel
In this paper, we present privacy distillation, a mechanism which allows patients to control the type and amount of information they wish to disclose to the healthcare providers for use in statistical models.
no code implementations • 31 Mar 2016 • Z. Berkay Celik, Patrick McDaniel, Rauf Izmailov, Nicolas Papernot, Ryan Sheatsley, Raquel Alvarez, Ananthram Swami
In this paper, we consider an alternate learning approach that trains models using "privileged" information--features available at training time but not at runtime--to improve the accuracy and resilience of detection systems.
17 code implementations • 8 Feb 2016 • Nicolas Papernot, Patrick McDaniel, Ian Goodfellow, Somesh Jha, Z. Berkay Celik, Ananthram Swami
Our attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the target DNN.
11 code implementations • 24 Nov 2015 • Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z. Berkay Celik, Ananthram Swami
In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs.