Quantcast
Channel: cs.CR updates on arXiv.org
Browsing all 1404 articles
Browse latest View live

Optimal Zero-Shot Detector for Multi-Armed Attacks

arXiv:2402.15808v2 Announce Type: replace-cross Abstract: This paper explores a scenario in which a malicious actor employs a multi-armed attack strategy to manipulate data samples, offering them...

View Article



Efficient local linearity regularization to overcome catastrophic overfitting

arXiv:2401.11618v2 Announce Type: replace-cross Abstract: Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to...

View Article

Towards Efficient Communication and Secure Federated Recommendation System...

arXiv:2401.03748v2 Announce Type: replace-cross Abstract: Federated Recommendation (FedRec) systems have emerged as a solution to safeguard users' data in response to growing regulatory concerns....

View Article

Toward Robust Imperceptible Perturbation against Unauthorized Text-to-image...

arXiv:2311.13127v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong...

View Article

Federated Heterogeneous Graph Neural Network for Privacy-preserving...

arXiv:2310.11730v4 Announce Type: replace-cross Abstract: The heterogeneous information network (HIN), which contains rich semantics depicted by meta-paths, has emerged as a potent tool for mitigating...

View Article


A Game-theoretic Framework for Privacy-preserving Federated Learning

arXiv:2304.05836v3 Announce Type: replace-cross Abstract: In federated learning, benign participants aim to optimize a global model collaboratively. However, the risk of \textit{privacy leakage} cannot...

View Article

Differentially Private Neural Tangent Kernels for Privacy-Preserving Data...

arXiv:2303.01687v2 Announce Type: replace-cross Abstract: Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with...

View Article

The NISQ Complexity of Collision Finding

arXiv:2211.12954v2 Announce Type: replace-cross Abstract: Collision-resistant hashing, a fundamental primitive in modern cryptography, ensures that there is no efficient way to find distinct inputs...

View Article


On the Robustness of Bayesian Neural Networks to Adversarial Attacks

arXiv:2207.06154v3 Announce Type: replace-cross Abstract: Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite...

View Article


Attention-GAN for Anomaly Detection: A Cutting-Edge Approach to Cybersecurity...

arXiv:2402.15945v2 Announce Type: replace Abstract: This paper proposes an innovative Attention-GAN framework for enhancing cybersecurity, focusing on anomaly detection. In response to the challenges...

View Article

Mitigating Fine-tuning Jailbreak Attack with Backdoor Enhanced Alignment

arXiv:2402.14968v2 Announce Type: replace Abstract: Despite the general capabilities of Large Language Models (LLMs) like GPT-4 and Llama-2, these models still request fine-tuning or adaptation with...

View Article

A Generalized Shuffle Framework for Privacy Amplification: Strengthening...

arXiv:2312.14388v2 Announce Type: replace Abstract: The shuffle model of local differential privacy is an advanced method of privacy amplification designed to enhance privacy protection with high...

View Article

A Modular Approach to Unclonable Cryptography

arXiv:2311.11890v2 Announce Type: replace Abstract: We explore a new pathway to designing unclonable cryptographic primitives. We propose a new notion called unclonable puncturable obfuscation (UPO)...

View Article


False Claims against Model Ownership Resolution

arXiv:2304.06607v4 Announce Type: replace Abstract: Deep neural network (DNN) models are valuable intellectual property of model owners, constituting a competitive advantage. Therefore, it is crucial...

View Article

Fair Ordering via Streaming Social Choice Theory

arXiv:2304.02730v3 Announce Type: replace Abstract: Prior work studies the question of ``fairly'' ordering transactions in a replicated state machine. Each of $n$ replicas receives transactions in a...

View Article


OpenAPI Specification Extended Security Scheme: A method to reduce the...

arXiv:2212.06606v2 Announce Type: replace Abstract: APIs have become the prominent technology of choice for achieving inter-service communications. The growth of API deployments has driven the urgency...

View Article

Model Predictive Control with adaptive resilience for Denial-of-Service...

arXiv:2402.18516v1 Announce Type: cross Abstract: In recent years, SCADA (Supervisory Control and Data Acquisition) systems have increasingly become the target of cyber attacks. SCADAs are no longer...

View Article


DevPhish: Exploring Social Engineering in Software Supply Chain Attacks on...

arXiv:2402.18401v1 Announce Type: cross Abstract: The Software Supply Chain (SSC) has captured considerable attention from attackers seeking to infiltrate systems and undermine organizations. There is...

View Article

Catastrophic Overfitting: A Potential Blessing in Disguise

arXiv:2402.18211v1 Announce Type: cross Abstract: Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial...

View Article

Modeling and Analysis of Crypto-Backed Over-Collateralized Stable Derivatives...

arXiv:2402.18119v1 Announce Type: cross Abstract: In decentralized finance (DeFi), stablecoins like DAI are designed to offer a stable value amidst the fluctuating nature of cryptocurrencies. We...

View Article
Browsing all 1404 articles
Browse latest View live




Latest Images