相关论文: SALSA: Attacking Lattice Cryptography with Transfo…

In-context learning (ICL) has emerged as a powerful capability of transformer-based language models, enabling them to perform tasks by conditioning on a small number of examples presented at inference time, without any parameter updates.…

We develop an unsupervised deep learning framework for real-time scalable and generalizable downlink beamforming in multi-user multiple-input single-output (MU-MISO) systems. The proposed semi-amortized lifted learning-to-optimize (SALLO)…

In this paper IEEE Learning Technology System Architecture (LTSA) for LMS software has been analyzed. It has been observed that LTSA is too abstract to be adapted in a uniform way by LMS developers. A Learners' Quanta based high level…

Encrypted control has been introduced to protect controller data by encryption at the stage of computation and communication, by performing the computation directly on encrypted data. In this article, we first review and categorize recent…

Quantum computing promises to revolutionize our understanding of the limits of computation, and its implications in cryptography have long been evident. Today, cryptographers are actively devising post-quantum solutions to counter the…

The Learning with Errors problem (LWE) is one of the main candidates for post-quantum cryptography. At Asiacrypt 2017, coded-BKW with sieving, an algorithm combining the Blum-Kalai-Wasserman algorithm (BKW) with lattice sieving techniques,…

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

Recent developments in Large Language Model (LLM) capabilities have brought great potential but also posed new risks. For example, LLMs with knowledge of bioweapons, advanced chemistry, or cyberattacks could cause violence if placed in the…

Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning…

Post-quantum cryptography currently rests on a small number of hardness assumptions, posing significant risks should any one of them be compromised. This vulnerability motivates the search for new and cryptographically versatile assumptions…

The rise of hardware-level security threats, such as side-channel attacks, hardware Trojans, and firmware vulnerabilities, demands advanced detection mechanisms that are more intelligent and adaptive. Traditional methods often fall short in…

Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as…

Federated Learning (FL) enables collaborative model training without centralizing client data, making it attractive for privacy-sensitive domains. While existing approaches employ cryptographic techniques such as homomorphic encryption,…

Before adopting a new large language model (LLM) architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be difficult to trust, often drawing conclusions from LLMs that are not meaningfully…

Quantum-based cryptographic protocols are often said to enjoy security guaranteed by the fundamental laws of physics. However, even carefully designed quantum-based cryptographic schemes may be susceptible to subtle attacks that are outside…

Securing enterprise networks presents challenges in terms of both their size and distributed structure. Data required to detect and characterize malicious activities may be diffused and may be located across network and endpoint devices.…

The security of public-key cryptosystems is mostly based on number theoretic problems like factorization and the discrete logarithm. There exists an algorithm which solves these problems in polynomial time using a quantum computer. Hence,…

The advent of quantum computing threatens the security of traditional encryption algorithms, motivating the development of post-quantum cryptography (PQC). In 2024, the National Institute of Standards and Technology (NIST) standardized…

Self-supervised learning (SSL) aims to find meaningful representations from unlabeled data by encoding semantic similarities through data augmentations. Despite its current popularity, theoretical insights about SSL are still scarce. For…

We investigate a specific security risk in FL: a group of malicious clients has impacted the model during training by disguising their identities and acting as benign clients but later switching to an adversarial role. They use their data,…