Zobrazeno 1 - 10
of 15 946
pro vyhledávání: '"P., Rajendran"'
Inspired by biological processes, neuromorphic computing utilizes spiking neural networks (SNNs) to perform inference tasks, offering significant efficiency gains for workloads involving sequential data. Recent advances in hardware and software have
Externí odkaz:
http://arxiv.org/abs/2411.04728
Autor:
Qiu, Liang, Chi, Wenhao, Xing, Xiaohan, Rajendran, Praveenbalaji, Li, Mingjie, Jiang, Yuming, Pastor-Serrano, Oscar, Yang, Sen, Wang, Xiyue, Ji, Yuanfeng, Wen, Qiang
Precision therapy for liver cancer necessitates accurately delineating liver sub-regions to protect healthy tissue while targeting tumors, which is essential for reducing recurrence and improving survival rates. However, the segmentation of hepatic s
Externí odkaz:
http://arxiv.org/abs/2411.02815
Sequence models have demonstrated the ability to perform tasks like channel equalization and symbol detection by automatically adapting to current channel conditions. This is done without requiring any explicit optimization and by leveraging not only
Externí odkaz:
http://arxiv.org/abs/2410.23882
Autor:
Rostami, Mohamadreza, Chen, Chen, Kande, Rahul, Li, Huimin, Rajendran, Jeyavijayan, Sadeghi, Ahmad-Reza
Publikováno v:
IEEE Security & Privacy ( Volume: 22, Issue: 4, July-Aug. 2024)
Hardware-level memory vulnerabilities severely threaten computing systems. However, hardware patching is inefficient or difficult postfabrication. We investigate the effectiveness of hardware fuzzing in detecting hardware memory vulnerabilities and h
Externí odkaz:
http://arxiv.org/abs/2410.22561
Autor:
Rostami, Mohamadreza, Zeitouni, Shaza, Kande, Rahul, Chen, Chen, Mahmoody, Pouya, Jeyavijayan, Rajendran, Sadeghi, Ahmad-Reza
Microarchitectural attacks represent a challenging and persistent threat to modern processors, exploiting inherent design vulnerabilities in processors to leak sensitive information or compromise systems. Of particular concern is the susceptibility o
Externí odkaz:
http://arxiv.org/abs/2410.22555
Autor:
Nimbekar, Anagha, Katti, Prabodh, Li, Chen, Al-Hashimi, Bashir M., Acharyya, Amit, Rajendran, Bipin
Spiking Neural Networks (SNNs) have emerged as a promising approach to improve the energy efficiency of machine learning models, as they naturally implement event-driven computations while avoiding expensive multiplication operations. In this paper,
Externí odkaz:
http://arxiv.org/abs/2410.16298
Autor:
Bouchoucha, Rached, Yahmed, Ahmed Haj, Patil, Darshan, Rajendran, Janarthanan, Nikanjam, Amin, Chandar, Sarath, Khomh, Foutse
Deep reinforcement learning (DRL) has shown success in diverse domains such as robotics, computer games, and recommendation systems. However, like any other software system, DRL-based software systems are susceptible to faults that pose unique challe
Externí odkaz:
http://arxiv.org/abs/2410.04322
Optimizing framerate for a given bitrate-spatial resolution pair in adaptive video streaming is essential to maintain perceptual quality while considering decoding complexity. Low framerates at low bitrates reduce compression artifacts and decrease d
Externí odkaz:
http://arxiv.org/abs/2410.00849
Light, weakly coupled bosonic particles such as axions can mediate long range monopole-dipole interactions between matter and spins. We propose a new experimental method using atom interferometry to detect such a force on a freely falling atom exerte
Externí odkaz:
http://arxiv.org/abs/2409.14793
Autor:
Rosati, Domenic, Edkins, Giles, Raj, Harsh, Atanasov, David, Majumdar, Subhabrata, Rajendran, Janarthanan, Rudzicz, Frank, Sajjad, Hassan
While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety-aligned LLMs are known to be vulnerable to training-time attacks such as supervised fine-tuning (SFT)
Externí odkaz:
http://arxiv.org/abs/2409.12914