密码学与安全

We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal…

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

We study privacy amplification by synthetic data release, a phenomenon in which differential privacy guarantees are improved by releasing only synthetic data rather than the private generative model itself. Recent work by Pierquin et al.…

Secure data join enables two parties with vertically distributed data to securely compute the joined table, allowing the parties to perform downstream Secure multi-party computation-based Data Analytics (SDA), such as training machine…

Respiratory monitoring is an extremely important task in modern medical services. Due to its significant advantages, e.g., non-contact, radar-based respiratory monitoring has attracted widespread attention from both academia and industry.…

Stealing attacks pose a persistent threat to the intellectual property of deployed machine-learning systems. Retrieval-augmented generation (RAG) intensifies this risk by extending the attack surface beyond model weights to knowledge base…

The use of neural networks in edge devices is increasing, which introduces new security challenges related to the neural networks' confidentiality. As edge devices often offer physical access, attacks targeting the hardware, such as…

One of the most difficult challenges in cybersecurity is eliminating Distributed Denial of Service (DDoS) attacks. Automating this task using artificial intelligence is a complex process due to the inherent class imbalance and lack of…

Federated Learning (FL) enables collaborative model training while preserving data privacy, but its classical cryptographic underpinnings are vulnerable to quantum attacks. This vulnerability is particularly critical in sensitive domains…

Federated learning (FL) has come forward as a critical approach for privacy-preserving machine learning in healthcare, allowing collaborative model training across decentralized medical datasets without exchanging clients' data. However,…

Certification Authority Authentication (CAA) is a safeguard against illegitimate certificate issuance. We show how shortcomings in CAA concepts and operational aspects undermine its effectiveness in preventing certificate misissuance. Our…

Detecting and classifying suspicious or malicious domain names and URLs is fundamental task in cybersecurity. To leverage such indicators of compromise, cybersecurity vendors and practitioners often maintain and update blacklists of known…

Evolving attacker capabilities demand realistic and continuously updated cyberattack emulation for threat-informed defense and security benchmarking. Towards automated attack emulation, this paper defines modular attack actions and a…

Cloud-native application platforms and latency-sensitive systems such as 5G Core networks rely heavily on certificate-based Public Key Infrastructure (PKI) and mutual TLS to secure service-to-service communication. While effective, this…

Denial-of-Service (DoS) conditions in enterprise networks are commonly attributed to malicious actors. However, availability can also be compromised by benign non-malicious insider behavior. This paper presents an empirical study of a…

Large language models (LLMs) have been widely adopted in modern software development lifecycles, where they are increasingly used to automate and assist code generation, significantly improving developer productivity and reducing…

Block space on the blockchain is scarce and must be allocated efficiently through block building. However, Ethereum's current block-building ecosystem, MEV-Boost, has become highly centralized due to integration, which distorts competition,…

When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security threat. By injecting malicious instructions into the data that…

Is module-lattice reduction better than unstructured lattice reduction? This question was highlighted as 'Q8' in the Kyber NIST standardization submission (Avanzi et al., 2021), as potentially affecting the concrete security of Kyber and…

As large language models (LLMs) expose systemic security challenges in high risk applications, including privacy leaks, bias amplification, and malicious abuse, there is an urgent need for a dynamic risk assessment and collaborative defence…