密码学与安全

Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed thresholds or perform clustering with a fixed number of clusters to…

We introduce a mathematical and cryptographic framework for exact recovery of noisy hidden paths in high dimensional discrete path spaces. The work is inspired by the path integral viewpoint, where global quantities arise from contributions…

Embedded neural-network inference can leak information through timing side channels, including leakage caused by the evaluation of activation functions. This work proposes a constant-time implementation methodology for activation functions…

Vision processing units and other commercial neural-network inference accelerators are increasingly deployed in safety-relevant edge applications, but their fault response under transient hardware disturbances remains poorly characterized…

The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such…

Security operations centers face persistent alert fatigue: in low-prevalence streams, even low false-positive rates generate substantial investigation load, while aggregate F1 scores obscure analyst burden. We introduce PACT, a Pareto-aware…

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…

Modern charging communication standards for electric vehicles include optional security controls such as TLS-based authentication and encryption. However, with tens of thousands of fast charging points deployed in any given country,…

Collaborative perception (CP) enables connected and autonomous vehicles to share sensor data and jointly reason about their environment. To defend against adversaries that fabricate or manipulate shared data, existing systems employ…

The Internet of Medical Things (IoMT) marks a shift toward decentralized healthcare, enabling continuous monitoring and personalized care through connected wearable and implantable devices. However, ensuring the trust and integrity of these…

Closed-weight generative services are increasingly deployed through query-based APIs, where users can obtain generated outputs while model parameters remain inaccessible. However, such deployment does not prevent model stealing: an attacker…

While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks. Existing static-oriented defenses struggle to handle evolving threats and incur prohibitive storage…

Security analysts routinely query system logs to detect threats and investigate incidents, but each log source uses its own semi-structured format: logs are cheap to produce, but expensive to use. The standard approach, building per-source…

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain…

Congestion controllers (CCs) are critical to network performance, and yet their robustness under adverse conditions remains insufficiently understood. While recent learning-based CCs have demonstrated strong performance in controlled…

Data leakage from API responses has drawn wide attention. APIs are often not fully regulated, making them easy to abuse. One common solution is to embed watermarks into API responses for traceability. However, existing watermarking methods…

We introduce baseSPIDER and SPIDER, private information retrieval (PIR) schemes that embody two technical advancements. The baseSPIDER protocol operates with a single server and a stateful client that performs pre-processing and stores…

Fuzz testing is the dominant technique for finding memory-safety vulnerabilities in C/C++ software, yet its effectiveness hinges on the quality of fuzz harnesses -- the programs that bridge fuzzers and library APIs. A growing body of tools…

Sandbox evasion remains a critical challenge for automated malware analysis, as modern malware employs environment checks to detect analysis platforms and suppress malicious behavior. Existing approaches rely on manually crafted bypass…

Understanding the functional graph of a nonlinear map over a finite domain is crucial for analyzing its dynamical complexity and potential applications in cryptography and pseudorandom generation. In this paper, we investigate the graph…