密码学与安全

Our evaluation shows that PoLO achieves \textbf{99\%} watermark detection accuracy for ownership verification, while preserving data privacy and cutting verification costs to just \textbf{1.5--10\%} of traditional methods. Forging PoLO…

Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns: fine-tuning with a few harmful data uploaded from the users can compromise the safety alignment of the model. The attack,…

Agent systems increasingly execute rather than advise. When an AI agent queries regulated data, invokes effectful tools, and mutates persistent state, correctness is not captured by whether a terminal output looks plausible. The operative…

We present CrossCommitVuln-Bench, a curated benchmark of 15 real-world Python vulnerabilities (CVEs) in which the exploitable condition was introduced across multiple commits - each individually benign to per-commit static analysis - but…

Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that…

Autonomous Vehicles (AVs) increasingly depend on Multi-Sensor Fusion (MSF) to combine complementary modalities such as cameras and LiDAR for robust perception. While this redundancy is intended to safeguard against single-sensor failures,…

Modern phishing campaigns increasingly evade snapshot-based URL classifiers using interaction gates (e.g., checkbox/slider challenges), delayed content rendering, and logo-less credential harvesters. This shifts URL triage from static…

Near-field millimeter-wave (mmWave) imaging is widely deployed in safety-critical applications such as airport passenger screening, yet its own security remains largely unexplored. This paper presents a systematic study of the adversarial…

The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…

Technology for security operations centers (SOCs) has a storied history of slow adoption due to concerns about trust and reliability. These concerns are amplified with artificial intelligence, particularly large language models (LLMs),…

Past attacks against industrial control systems (ICS) show that adversaries often target both the ICS network and the physical process to achieve potential catastrophic impact. To secure ICS, intrusion detection systems promise timely…

The proliferation of Internet of Things (IoT) devices has significantly expanded attack surfaces, making IoT ecosystems particularly susceptible to sophisticated cyber threats. To address this challenge, this work introduces A-THENA, a…

Contemporary cybersecurity governance assumes that professionals apply risk reasoning. Yet major organisational failures persist despite investment in tools, staffing, and credentials. This study investigates the structural source of that…

Differential privacy (DP) is a mathematical framework that guarantees individual privacy; however, systematic evaluation of its impact on statistical utility in survival analyses remains limited. In this study, we systematically evaluated…

Model Context Protocol (MCP) is increasingly adopted for tool-integrated LLM agents, but its multi-layer design and third-party server ecosystem expand risks across tool metadata, untrusted outputs, cross-tool flows, multimodal inputs, and…

Protecting patient privacy in clinical narratives is essential for enabling secondary use of healthcare data under regulations such as GDPR and HIPAA. While manual de-identification remains the gold standard, it is costly and slow,…

Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean…

Deep learning has emerged as a powerful approach for malware detection, demonstrating impressive accuracy across various data representations. However, these models face critical limitations in real-world, non-stationary environments where…

Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new risks for sensitive information leakage. We introduce…

Automated code vulnerability detection is critical for software security, yet existing approaches face a fundamental trade-off between detection accuracy and computational cost. We propose a heterogeneous multi-agent architecture inspired…