密码学与安全

We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…

Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting strategies. Existing prompt engineering improves functional correctness but rarely ensures…

The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to…

Android malware detectors often degrade after deployment because of concept drift, while full retraining at each maintenance step is costly. We propose a chronological adaptive maintenance framework that models deployment-time maintenance…

The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which…

Deep-research agents, i.e., systems that rely on multi-agent pipelines to iteratively retrieve, synthesize, and cite Web content in order to produce structured reports, are rapidly replacing traditional search for both routine and complex…

Many existing Artificial Intelligence (AI) solutions on mobile devices rely on an extensive collection of sensitive data, raising privacy concerns and often requiring storage for both context and model improvement. Apple's Private Cloud…

Along with the recent rise in popularity of Electric Vehicles (EVs), Electric Vehicle Supply Equipment (EVSE) has emerged as a new target for cyber attacks. Therefore, ensuring the security and integrity of network communication between…

Electric Vehicles (EVs) have emerged as significant disruptors in the transportation sector over the past decade. Their growing popularity and adoption are accompanied by capital expenditures to deploy charging infrastructure. EV charging…

The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented autonomous execution capabilities for LLM Agents by integrating external open-domain…

Cryptographic operations are an essential component of cloud security architectures; their comprehensive performance characterization across different cloud services, hardware architectures, and programming language implementations remains…

Federated learning (FL) enables collaborative model training by aggregating local updates without requiring raw data sharing. However, prior studies have shown that servers can exploit gradient inversion to compromise user privacy or…

Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic…

In cybersecurity, vulnerability assessment has typically focused on identifying and measuring vulnerabilities within digital assets and technical infrastructures. However, there is growing recognition that this approach alone is inadequate…

In this work, we propose a data-driven image encryption framework that identifies chaotic maps directly from data using the SINDy-PI algorithm. Unlike conventional encryption schemes relying on predefined maps, our method learns the full…

AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email,…

Graph neural networks (GNNs) have achieved remarkable success in relational learning. However, their vulnerability to graph backdoor attacks (GBAs) poses a significant barrier to broader adoption in high-stakes applications. Despite recent…

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…

Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire waveform densely throughout optimization. In this work, we investigate the necessity of such…