密码学与安全

We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized software components, overwrote a system registry, overrode a prior negative decision from an oversight agent, and…

This paper presents a system combining symbolic execution (KLEE) with a 4-agent multi-LLM architecture for detecting memory vulnerabilities in Rust unsafe code. A central challenge we address is the incomplete-code problem: CVE database…

Privacy policies are intended to inform users about how software systems collect and handle data, yet they often remain vague or incomplete. This paper presents an empirical study of patterns in log-related statements within privacy…

Autonomous large language model (LLM) agents such as OpenClaw are pushing agentic commerce from human-supervised assistance toward machine actors that can negotiate, purchase services, manage digital assets, and execute transactions across…

Autonomous agents can produce harmful behavioral patterns from individually valid requests -- a threat class per-request policy evaluation cannot address, because stateless engines evaluate each request in isolation. We present ACP, a…

Spiking Neural Networks (SNNs) are energy-efficient counterparts of Deep Neural Networks (DNNs) with high biological plausibility, as information is transmitted through temporal spiking patterns. The core element of an SNN is the spiking…

GitHub Security Advisories (GHSA) have become a central component of open-source vulnerability disclosure and are widely used by developers and security tools. A distinctive feature of GHSA is that only a fraction of advisories are reviewed…

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

The Open Network (TON) blockchain employs an asynchronous execution model that introduces unique security challenges for smart contracts. A primary concern is race conditions arising from unpredictable message processing order. While…

Large language models(LLMs) are increasingly integrated with external systems through the Model Context Protocol(MCP),which standardizes tool invocation and has rapidly become a backbone for LLM-powered applications. While this paradigm…

We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM agent X on the task of Cyber Threat Investigation through security questions derived from investigation graphs. Real-world security analysts must sift through a large number…

The proliferation of electric vehicles in recent years has significantly expanded the charging infrastructure while introducing new security risks to both vehicles and chargers. In this paper, we investigate the security of major charging…

Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to embeddings (commonly regarded as privacy-preserving), model…

Traditional Insurance, a popular approach of financial risk management, has suffered from the issues of high operational costs, opaqueness, inefficiency and a lack of trust. Recently, blockchain-enabled "parametric insurance" through…

Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation, autonomous agents, and AI assistants. However, security…

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature…

Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct prohibited content. In…

System auditing on Android faces two problems. First, existing syscall tracers lose events under load, silently overwriting entries faster than a user space reader can drain them. Second, security-relevant application behavior is mediated…

Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradigm also introduces new safety challenges. Since only a subset…

Lattice reduction smooths the Gram-Schmidt profile, and we use majorization to describe the local swap mechanism behind that smoothing. In this language, each non-degenerate Lov\'asz swap acts as a T-transform on the log-norm profile. As a…