Related papers: Positional-Unigram Byte Models for Generalized TLS…
This paper presents applicability of Strong Stationary Times (SST) techniques in the area of cryptography. The applicability is in three areas: *) Propositions of a new class of cryptographic algorithms (pseudo-random permutation…
Model fingerprinting has emerged as a promising paradigm for claiming model ownership. However, robustness evaluations of these schemes have mostly focused on benign perturbations such as incremental fine-tuning, model merging, and…
Fingerprinting large language models (LLMs) is essential for verifying model ownership, ensuring authenticity, and preventing misuse. Traditional fingerprinting methods often require significant computational overhead or white-box…
When monitoring a cyber-physical system (CPS) from a remote server, keeping the monitored data secret is crucial, particularly when they contain sensitive information, e.g., biological or location data. Recently, Banno et al. (CAV'22)…
A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their original settings, but their attacks vary substantially in…
The efficient operation of modern cellular networks hinges on the accurate analysis of spatio-temporal traffic data. Mastering these patterns is essential for core network functions, chiefly forecasting future load to pre-empt congestion…
Big data has been a pervasive catchphrase in recent years, but dealing with data scarcity has become a crucial question for many real-world deep learning (DL) applications. A popular methodology to efficiently enable the training of DL…
Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel fingerprinting framework that leverages the behavioral patterns…
Secure signal processing is becoming a de facto model for preserving privacy. We propose a model based on the Fully Homomorphic Encryption (FHE) technique to mitigate security breaches. Our framework provides a method to perform a Fast…
Within the simultaneous message passing model of communication complexity, under a public-coin assumption, we derive the minimum achievable worst-case error probability of a classical fingerprinting protocol with one-sided error. We then…
When dedicated positioning systems, such as GPS, are unavailable, a mobile device has no choice but to fall back on its cellular network for localization. Due to random variations in the channel conditions to its surrounding base stations…
Website fingerprinting enables an attacker to infer which web page a client is browsing through encrypted or anonymized network connections. We present a new website fingerprinting technique based on random decision forests and evaluate…
Recent advances confirm that large language models (LLMs) can achieve state-of-the-art performance across various tasks. However, due to the resource-intensive nature of training LLMs from scratch, it is urgent and crucial to protect the…
We present a general method for finding loss-tolerant teleportation on large, entangled stabilizer states using only single-qubit measurements, known as \emph{stabilizer pathfinding} (SPF). For heralded loss, SPF is shown to generate…
Travel mode identification (TMI) from GPS trajectories is critical for urban intelligence, but is hampered by the high cost of annotation, leading to severe label scarcity. Prevailing semi-supervised learning (SSL) methods are ill-suited…
Accurate mobile device localization is critical for emerging 5G/6G applications such as autonomous vehicles and augmented reality. In this paper, we propose a unified localization method that integrates model-based and machine learning…
Wireless localization for mobile device has attracted more and more interests by increasing the demand for location based services. Fingerprint-based localization is promising, especially in non-Line-of-Sight (NLoS) or rich scattering…
Accurate and tamper-resistant timestamps are essential for applications demanding verifiable chronological ordering, such as legal documentation and digital intellectual property protection. Classical timestamp protocols rely on…
This paper proposes Characteristic Examples for effectively fingerprinting deep neural networks, featuring high-robustness to the base model against model pruning as well as low-transferability to unassociated models. This is the first work…
In recent years, several probabilistic techniques have been applied to various debugging problems. However, most existing probabilistic debugging systems use relatively simple statistical models, and fail to generalize across multiple…