密码学与安全

Generative AI (GenAI) systems store and process client data in three distinct ways: in the model's parameters through training and memorisation, in the context window during a live session, and in knowledge databases for retrieval-augmented…

Algorithmic Complexity Vulnerabilities (ACVs) arise when adversarial inputs trigger worst-case execution behavior, causing severe performance degradation or Denial-of-Service conditions. A key but underexplored source is shadow complexity:…

As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse. We present BioSecBench-Refusal, a benchmark for risk identification and refusal behavior for biological research…

Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-bit schemes for distinguishing synthetic text from human writing and multi-bit schemes for…

Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such as tool-use APIs, this separation arises naturally: agents…

Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints.…

Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution. This integration also creates a new path to compromise:…

AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security has primarily focused on indirect prompt injection (IPI). Its most well-studied category is…

To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age estimation, and race classification). Each trained model is…

Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this has improved the agent's functionality and continuity across…

This paper develops a representation-theoretic perspective on cryptographic protocols. The focus is not solely on the computability of the abstract value as an extensional property, but on the algorithmic structure of its presentation in a…

Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning. Cybersecurity Knowledge Graphs (CSKGs) provide a structured…

Systems that process medical data should be meticulously secured. Yet, network services in healthcare environments often fail to implement basic security measures. For example, previous studies showed that network segmentation flaws led to…

Look-ahead bias (using information from after a decision epoch to make the decision at that epoch) is the dominant way a backtest or a machine-learning evaluation flatters a system that will disappoint in deployment. The field manages it…

Cellular data billing is a core operational mechanism for mobile Internet service providers (ISPs), and a policy gap that excludes a specific protocol from usage accounting can lead to a practical security threat. Some cellular ISPs treat…

With the increasing threat of malware across various software related domains, malware detection and classification is critical to determine the response actions. Different strategies have been adopted to address the challenge of malware…

LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace. They typically rely on small non-compilable snippets, focus on binary classification (vulnerable or not), and do not account for the…

Data brokers are a largely American phenomenon. They collect vast amounts of personal information about most adult U.S. consumers, mainly without the latter's knowledge or consent. Accumulated data can be sold to anyone, including…

Enterprise security teams commonly summarize remediation through mean time to remediate (MTTR), SLA compliance, dwell time, or detection delay. These metrics are useful, but they can hide how fixes actually reach the estate: continuously,…

Adversarial purification is a defense technique that employs generative models to remove adversarial perturbations. Current methods often rely on powerful generators, typically diffusion models, and focus on reducing the gap between…