密码学与安全

Recent work has demonstrated that machine unlearning in Large Language Models (LLMs) fails to generalize across languages: knowledge erased in one language frequently remains accessible through others. However, the underlying cause of this…

Distributed denial-of-service (DDoS) attacks threaten the availability of Internet of Things (IoT) infrastructures, particularly under resource-constrained deployment conditions. Although transfer learning models have shown promising…

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…

Markov chains model a wide range of user behaviors. However, generating accurate Markov chain models requires substantial user data, and sharing these models without privacy protections may reveal sensitive information about the underlying…

Modern infrastructures rely on software systems that remain vulnerable to cyberattacks. These attacks frequently exploit vulnerabilities documented in repositories such as MITRE's Common Vulnerabilities and Exposures (CVE). However, Cyber…

Data privacy is important in the AI era, and differential privacy (DP) is one of the golden solutions. However, DP is typically applicable only if data have a bounded underlying distribution. We address this limitation by leveraging…

Training-data poisoning attacks can induce targeted, undetectable failure in deep neural networks by corrupting a vanishingly small fraction of training labels. We demonstrate this on acoustic vehicle classification using the MELAUDIS urban…

The current generation of large language models produces sophisticated social-engineering content that bypasses standard text screening systems in business communication platforms. Our proposed solution for mail gateway and endpoint…

Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that…

The General Data Protection Regulation (GDPR) requires organisations to notify supervisory authorities of personal data breaches within 72 hours of discovery. Meeting this strict deadline is challenging because incident responders must…

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Cloud-edge AI must jointly satisfy model compression and security under tight device budgets. While Tensor-Train Decomposition (TTD) shrinks on-device models, prior selective-encryption studies largely assume dense weights, leaving its…

Distributed storage architectures are foundational to modern cloud-native infrastructure, yet a critical operational bottleneck persists within disaster recovery (DR) workflows: the dependence on content-based cryptographic hashing for data…

Blockchains are widely used for secure transaction processing, but their scalability remains limited, and existing multichain designs are typically static even as demand and capacity shift. We cast blockchain configuration as a multiagent…

Alpha-Root is a cybersecurity-focused dataset collected in a single shot from the Common Crawl web graph using community detection. Unlike iterative content-scoring approaches like DeepSeekMath, we mine quality domains directly from the web…

We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News users and Anthropic Interviewer participants at high precision, given pseudonymous online…

Analysts in Security Operations Centers routinely query massive telemetry streams using Kusto Query Language (KQL). Writing correct KQL requires specialized expertise, and this dependency creates a bottleneck as security teams scale. This…

Autonomous digital entities require deterministic identity mechanisms that avoid persistent storage of high-value master secrets, while supporting credential rotation and cryptographic agility across heterogeneous systems. Existing…

Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms such as differential privacy (DP) reduce this leakage, but…

The digital transformation of power systems is accelerating the adoption of IEC 61850 standard. However, its communication protocols, including Sampled Values (SV), lack built-in security features such as authentication and encryption,…