密码学与安全

Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks, in which adversarial prompts coerce models into generating harmful, unethical, or policy-violating outputs. Such attacks pose…

Windows Component Object Model (COM) services run with elevated privileges and are widely accessible to authenticated users, making race conditions in these binaries a critical surface for local privilege escalation. We present SLYP, an…

The open-source ecosystem has accelerated the democratization of Large Language Models (LLMs) through the public distribution of specialized Low-Rank Adaptation (LoRA) modules. However, integrating these third-party adapters often induces…

Atomic swaps are a fundamental primitive for the trustless exchange of digital assets across blockchains: they guarantee that either both parties receive the agreed assets or neither party transfers. While this all-or-nothing guarantee is…

For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client's input. However, securely computing nonlinear layers remains a major…

As security demands increase, the importance of secure computation technologies grows, yet these technologies can often seem overwhelming to practitioners. Furthermore, many approaches focus only on a single technology, potentially…

Replacing conventional devices with smart ones has many advantages, e.g., a seamless integration of physical objects into the users digital environment or improved modes of use. However, if a conventional device is replaced by a smart…

Industrial Control Protocols (ICPs) are critical to the reliability and stability of industrial infrastructure, yet their security is fundamentally compromised by a specification-blindness bottleneck. Modern fuzzers, constrained by…

The pervasive integration of AI has enabled Offensive AI: the exploitation of AI for malicious ends across the cyber-kill chain. A critical manifestation is the user attribute inference attack, where AI infers sensitive Personally…

Today, advances in medical technology extensively utilize 3D volume data for accurate and efficient diagnostics. However, sharing these data across networks in telemedicine poses significant security risks of data tampering and unauthorized…

Modern malware detection pipelines rely on continuous data ingestion and machine learning to counter the high volume of novel threats. This work investigates a realistic gray-box poisoning threat model targeting these pipelines. Using the…

Wi-Fi signals can be exploited by adversaries as a sensing side channel to eavesdrop on physical information. By monitoring propagation effects of radio waves within the victim's environment, attackers can remotely infer sensitive…

Cyber threats are rapidly increasing, expanding their impact from large-scale enterprises to government services and individual users, making robust security systems increasingly essential. However, a significant shortage of skilled…

This study investigates the rapid centralization of the Ethereum builder market under the Proposer-Builder Separation (PBS) architecture. We argue that existing research, by focusing predominantly on influential order flows, lacks a…

Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduces a new attack surface: the routing mechanism that…

The growth of networked and IoT systems has intensified cyber-security threats and exposed the limits of traditional signature-based intrusion detection. Although machine-learning-based intrusion detection systems often report strong…

Blockchain-based IoT data sharing systems increasingly adopt a hybrid architecture in which a permissioned ledger stores tamper-evident metadata while encrypted payloads are placed in content-addressed storage. In such systems, a central…

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content…

Vulnerability detection for C/C++ code increasingly relies on heavy representations such as code graphs and deep models, while many practical workflows still benefit from fast and reproducible ranking baselines for human triage. This…

Recent LLM-based systems have made automated vulnerability repair increasingly practical, but two challenges remain. First, without strong signals about where a bug originates, repair agents drift toward shallow edits that silence the…