Zobrazeno 1 - 10
of 375
pro vyhledávání: '"KOUSHANFAR, FARINAZ"'
Protecting integrated circuits (ICs) from piracy and theft throughout their lifecycle is a persistent and complex challenge. In order to safeguard against illicit piracy attacks, this work proposes a novel framework utilizing Non-Fungible Tokens (NFT
Externí odkaz:
http://arxiv.org/abs/2412.06726
Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific output on any input which includes the trigger. With the increasing relevance of deep networks which
Externí odkaz:
http://arxiv.org/abs/2411.12914
Vibrometry-based side channels pose a significant privacy risk, exploiting sensors like mmWave radars, light sensors, and accelerometers to detect vibrations from sound sources or proximate objects, enabling speech eavesdropping. Despite various prop
Externí odkaz:
http://arxiv.org/abs/2411.10034
Autor:
Ahmed, Anees, Sheybani, Nojan, Moreno, Davi, Njungle, Nges Brian, Gong, Tengkai, Kinsy, Michel, Koushanfar, Farinaz
Collision-resistant, cryptographic hash (CRH) functions have long been an integral part of providing security and privacy in modern systems. Certain constructions of zero-knowledge proof (ZKP) protocols aim to utilize CRH functions to perform cryptog
Externí odkaz:
http://arxiv.org/abs/2411.06350
Autor:
Juels, Ari, Koushanfar, Farinaz
We propose protected pipelines or props for short, a new approach for authenticated, privacy-preserving access to deep-web data for machine learning (ML). By permitting secure use of vast sources of deep-web data, props address the systemic bottlenec
Externí odkaz:
http://arxiv.org/abs/2410.20522
Autor:
Zhang, Ruisi, Koushanfar, Farinaz
The widely adopted and powerful generative large language models (LLMs) have raised concerns about intellectual property rights violations and the spread of machine-generated misinformation. Watermarking serves as a promising approch to establish own
Externí odkaz:
http://arxiv.org/abs/2410.19096
This paper presents AutoMarks, an automated and transferable watermarking framework that leverages graph neural networks to reduce the watermark search overheads during the placement stage. AutoMarks's novel automated watermark search is accomplished
Externí odkaz:
http://arxiv.org/abs/2407.20544
Physical design watermarking on contemporary integrated circuit (IC) layout encodes signatures without considering the dense connections and design constraints, which could lead to performance degradation on the watermarked products. This paper prese
Externí odkaz:
http://arxiv.org/abs/2404.18407
Autor:
Huo, Mingjia, Somayajula, Sai Ashish, Liang, Youwei, Zhang, Ruisi, Koushanfar, Farinaz, Xie, Pengtao
Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts. Watermarking is pivotal in this context, which involves embedding hidden
Externí odkaz:
http://arxiv.org/abs/2402.18059
Autor:
Zhang, Ruisi, Koushanfar, Farinaz
This paper introduces EmMark,a novel watermarking framework for protecting the intellectual property (IP) of embedded large language models deployed on resource-constrained edge devices. To address the IP theft risks posed by malicious end-users, EmM
Externí odkaz:
http://arxiv.org/abs/2402.17938