Yigitcan Kaya

According to our database, Yigitcan Kaya authored at least 19 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Demystifying Behavior-Based Malware Detection at Endpoints.

Yigitcan Kaya, Yizheng Chen, Shoumik Saha, Fabio Pierazzi, Lorenzo Cavallaro, David A. Wagner, Tudor Dumitras

CoRR, 2024

Understanding, Uncovering, and Mitigating the Causes of Inference Slowdown for Language Models.

Kamala Varma, Arda Numanoglu, Yigitcan Kaya, Tudor Dumitras

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2024

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness.

Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi, Tudor Dumitras

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds.

Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Sicheng Zhu, Furong Huang, Tudor Dumitras

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

The Limitations of Deep Learning Methods in Realistic Adversarial Settings.

Yigitcan Kaya

PhD thesis, 2023

Adversarial Robustness of Learning-based Static Malware Classifiers.

Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi

CoRR, 2023

2022

Generating Distributional Adversarial Examples to Evade Statistical Detectors.

Yigitcan Kaya, Muhammad Bilal Zafar, Sergül Aydöre, Nathalie Rauschmayr, Krishnaram Kenthapadi

Proceedings of the International Conference on Machine Learning, 2022

2021

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes.

Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Tudor Dumitras

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

When Does Data Augmentation Help With Membership Inference Attacks?

Yigitcan Kaya, Tudor Dumitras

Proceedings of the 38th International Conference on Machine Learning, 2021

A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference.

Sanghyun Hong, Yigitcan Kaya, Ionut-Vlad Modoranu, Tudor Dumitras

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

On the Effectiveness of Regularization Against Membership Inference Attacks.

Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras

CoRR, 2020

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping.

Sanghyun Hong, Varun Chandrasekaran, Yigitcan Kaya, Tudor Dumitras, Nicolas Papernot

CoRR, 2020

How to 0wn the NAS in Your Spare Time.

Sanghyun Hong, Michael Davinroy, Yigitcan Kaya, Dana Dachman-Soled, Tudor Dumitras

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks.

Sanghyun Hong, Pietro Frigo, Yigitcan Kaya, Cristiano Giuffrida, Tudor Dumitras

Proceedings of the 28th USENIX Security Symposium, 2019

Shallow-Deep Networks: Understanding and Mitigating Network Overthinking.

Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

How to Stop Off-the-Shelf Deep Neural Networks from Overthinking.

Yigitcan Kaya, Tudor Dumitras

CoRR, 2018

Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks.

Sanghyun Hong, Michael Davinroy, Yigitcan Kaya, Stuart Nevans Locke, Ian Rackow, Kevin Kulda, Dana Dachman-Soled, Tudor Dumitras

CoRR, 2018

When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks.

Octavian Suciu, Radu Marginean, Yigitcan Kaya, Hal Daumé III, Tudor Dumitras

Proceedings of the 27th USENIX Security Symposium, 2018

Too Big to FAIL: What You Need to Know Before Attacking a Machine Learning System.

Tudor Dumitras, Yigitcan Kaya, Radu Marginean, Octavian Suciu

Proceedings of the Security Protocols XXVI, 2018