密码学与安全
We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We develop a general theory that characterizes the worst-case privacy loss of an…
Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for privacy-sensitive applications. With the rapid adoption of large language models (LLMs), federated…
Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting against them - attack selection - is particularly concerning. To study this, we let a red team…
The rapid expansion of internet of things (IoT) devices has created a pervasive ecosystem where encrypted wireless communications serve as the primary privacy and security protection mechanism. While encryption effectively protects message…
As LLMs rapidly advance and enter real-world use, their privacy implications are increasingly important. We study an authorship de-anonymization threat: using LLMs to link anonymous documents to their authors, potentially compromising…
A proof of the security of the Bitcoin protocol is made rigorous, and simplified in certain parts. A computational model in which an adversary can delay transmission of blocks by time $\Delta$ is considered. The protocol is generalized to…
Replay and rollback attacks threaten cloud application integrity by reintroducing authentic yet stale data through an untrusted storage interface to compromise application decision-making. Prior security frameworks mitigate these attacks by…
The Open Network (TON) is a high-performance blockchain platform designed for scalability and efficiency, leveraging an asynchronous execution model and a multi-layered architecture. While TON's design offers significant advantages, it also…
Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…
Web3 systems expose a fundamentally different security landscape from centralized platforms, characterized by composability, pseudonymous identities, decentralized governance, and rapidly evolving attack strategies that span social,…
Digitization increases business opportunities and the risk of companies being victims of devastating cyberattacks. Therefore, managing risk exposure and cybersecurity strategies is essential for digitized companies that want to survive in…
Cybersecurity planning is challenging for digitized companies that want adequate protection without overspending money. Currently, the lack of investments and perverse economic incentives are the root cause of cyberattacks, which results in…
Most programs compiled to WebAssembly (Wasm) today are written in unsafe languages like C and C++. Unfortunately, memory-unsafe C code remains unsafe when compiled to Wasm -- and attackers can exploit buffer overflows and use-after-frees in…
Smart contracts deployed on blockchains such as Ethereum routinely manage large amounts of assets, making their security critical. Empirical studies show that real-world attacks often exploit flaws in the business logic of contracts that…
According to constructivist theory, students learn software security more effectively when examples are grounded in their own code. Generic examples often fail to connect with students' prior work, limiting engagement and understanding.…
The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing frameworks are inadequately equipped to address. We present MCPThreatHive, an open-source platform…
How do security scanners perform on real-world code? We present RealVuln, the first open-source benchmark comparing Rule-Based SAST, General-Purpose LLMs, and Security-Specialized scanners on 26 intentionally vulnerable Python repositories…
European digital sovereignty and security increasingly depends on whether high-impact decisions can be grounded in location evidence that remains credible under adversarial pressure. This paper frames a cross-sector analysis as a…
We propose a novel end-to-end privacy-preserving framework, instantiated by three efficient protocols for different deployment scenarios, covering both input and output privacy, for the vertically split scenario in federated learning (FL),…
The United States designates Food and Agriculture as one of sixteen critical infrastructure sectors, yet no mandatory cybersecurity requirements exist for agricultural operations and no formal threat model has been published for Controlled…