密码学与安全

Constant-size cryptographic evidence records are increasingly used to build audit trails for regulated AI workloads in clinical, pharmaceutical, and financial settings, where each execution is summarized by a compact, verifiable record of…

Regulated AI workflows (such as clinical trials, medical decision support, and financial compliance) must satisfy strict auditability and integrity requirements. Existing audit-trail mechanisms rely on variable-length records, bulky…

Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training distributions and adapt to…

Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNN) possible. However, the performance of these methods remain limited by their heavy…

Verifiable Secret Sharing (VSS) has been widespread in Distributed Privacy-preserving Machine Learning (DPML), because invalid shares from malicious dealers or participants can be recognized by verifying the commitment of the received…

Gradient inversion attacks are often presented as a serious privacy threat in federated learning, with recent work reporting increasingly strong reconstructions under favorable experimental settings. However, it remains unclear whether such…

Intrusion Detection and Prevention Systems (IDS/IPS) in large enterprises can generate hundreds of thousands of alerts per hour, overwhelming analysts with logs requiring rapidly evolving expertise. Conventional machine-learning detectors…

Penetration testing refers to the process of simulating hacker attacks to evaluate the security of information systems . This study aims not only to clarify the theoretical foundations of penetration testing but also to explain and…

Federated Learning with client-level differential privacy (DP) provides a promising framework for collaboratively training models while rigorously protecting clients' privacy. However, classic approaches like DP-FedAvg struggle when clients…

Due to the distributed nature of Federated Learning (FL) systems, each local client has access to the global model, which poses a critical risk of model leakage. Existing works have explored injecting watermarks into local models to enable…

The recent proliferation of blockchain-based decentralized applications (DApp) has catalyzed transformative advancements in distributed systems, with extensive deployments observed across financial, entertainment, media, and cybersecurity…

Privacy preservation in Internet of Things (IoT) systems requires the use of privacy-enhancing technologies (PETs) built from innovative technologies such as cryptography and artificial intelligence (AI) to create techniques called privacy…

Identifying LLM-generated code through watermarking poses a challenge in preserving functional correctness. Previous methods rely on the assumption that watermarking high-entropy tokens effectively maintains output quality. Our analysis…

Multimodal foundation models (MFMs) integrate diverse data modalities to support complex and wide-ranging tasks. However, this integration also introduces distinct safety and security challenges. In this paper, we unify the concepts of…

Smart contracts with external data are crucial for functionality but pose security and reliability concerns. Statistical and quantitative studies on this interaction are scarce. To address this gap, we analyzed 10,500 smart contracts,…

As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks. However, there is no…

Large language models (LLMs) are increasingly deployed in security-sensitive applications, yet remain vulnerable to backdoor attacks. However, existing backdoor defenses are difficult to operationalize for Backdoor Defense-as-a-Service…

This project explores large language models (LLMs) for anomaly detection across heterogeneous log sources. Traditional intrusion detection systems suffer from high false positive rates, semantic blindness, and data scarcity, as logs are…

LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up…

Recent progress in ML and LLMs has improved vulnerability detection, and recent datasets have reduced label noise and unrelated code changes. However, most existing approaches still operate at the function level, where models are asked to…