Related papers: Clap: a Semantic-Preserving Optimizing eDSL for Pl…
Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain. CLIP, a large-scale vision-language model, performs well in FSL on image-text embedding similarities, but it is susceptible to…
In previous work, we introduced a 2D localization algorithm called CLAP, Clustering to Localize Across $n$ Possibilities, which was used during our championship win in RoboCup 2024, an international autonomous humanoid soccer competition.…
This paper presents a novel method that leverages a visual-language model, CLIP, as a data source for zero-shot anomaly detection. Tremendous efforts have been put towards developing anomaly detectors due to their potential industrial…
Intellectual Property (IP) piracy, overbuilding, reverse engineering, and hardware Trojan are serious security concerns during integrated circuit (IC) development. Logic locking has proven to be a solid defence for mitigating these threats.…
Zero-knowledge proofs (ZKPs) have evolved from a theoretical cryptographic concept into a powerful tool for implementing privacy-preserving and verifiable applications without requiring trust assumptions. Despite significant progress in the…
Optimizing expensive, non-convex, black-box Lipschitz continuous functions presents significant challenges, particularly when the Lipschitz constant of the underlying function is unknown. Such problems often demand numerous function…
Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalability-completeness…
This paper introduces a scalable and secure contract-enforcement mechanism, called Cop, which can be applied to a broad range of multi-agent systems including small and large systems, time-critical systems, and systems-of-systems. Cop…
Logic Encryption is one of the most popular hardware security techniques which can prevent IP piracy and illegal IC overproduction. It introduces obfuscation by inserting some extra hardware into a design to hide its functionality from…
The state-of-the-art approach to manage blockchains is to process blocks of transactions in a shared-nothing environment. Although blockchains have the potential to provide various services for high-performance computing (HPC) systems, HPC…
To address the large amount of energy wasted by blockchains, we propose a decentralized consensus protocol for blockchains in which the computation can be used to search for good approximate solutions to any optimization problem. Our…
This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning. The main objective is twofold: first, to evaluate the robustness of CLIP, and…
Dynamic node classification is critical for modeling evolving systems like financial transactions and academic collaborations. In such systems, dynamically capturing node information changes is critical for dynamic node classification,…
Unsupervised action segmentation has recently pushed its limits with ASOT, an optimal transport (OT)-based method that simultaneously learns action representations and performs clustering using pseudo-labels. Unlike other OT-based…
Bug reproduction is critical in the software debugging and repair process, yet the majority of bugs in open-source and industrial settings lack executable tests to reproduce them at the time they are reported, making diagnosis and…
Simultaneous Localization and Planning (SLAP) under process and measurement uncertainties is a challenge. It involves solving a stochastic control problem modeled as a Partially Observed Markov Decision Process (POMDP) in a general…
Existing education systems are facing a threat of question paper leaking (QPL) in the exam which jeopardizes the quality of education. Therefore, it is high time to think about a more secure and flexible question sharing system which can…
This thesis proposes techniques aiming to make blockchain technologies and smart contract platforms practical by improving their scalability, latency, and privacy. This thesis starts by presenting the design and implementation of…
Constraint Logic Programming (CLP) is a language scheme for combining two declarative paradigms: constraint solving and logic programming. Concurrent Constraint Programming (CCP) is a declarative model for concurrency where agents interact…
Elliptic curve cryptography (ECC) is a widely established cryptographic technique, recognized for its effectiveness and reliability across a broad range of applications such as securing telecommunications or safeguarding cryptocurrency…