密码学与安全

Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture how safety properties evolve under sustained adversarial interaction. We present ADVERSA,…

Collaborative healthcare research across multiple institutions increasingly requires diverse clinical datasets, but cross-border data sharing is strictly constrained by privacy regulations. Federated learning (FL) enables model training…

AI agents that execute tasks via tool calls frequently hallucinate results - fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge…

Software supply-chain security requires provenance mechanisms that support reproducibility and vulnerability assessment under dynamic execution conditions. Conventional Software Bills of Materials (SBOMs) provide static dependency…

Most OAuth service providers, such as Google and Microsoft, offer only a limited range of coarse-grained data access. As a result, third-party OAuth applications often end up accessing more user data than necessary, even if their developers…

Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models (e.g., image classifiers), LLM-based agents with…

Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift -- unseen host/subnet IP reassignment in an otherwise fixed enterprise scenario -- and evaluate…

A common problem in private data analysis is the partition selection problem, where each user holds a set of partitions (e.g. keys in a GROUP BY operation) from a possibly unbounded set. The challenge here is in maximizing the set of…

Is robot cybersecurity broken by AI? Consumer robots -- from autonomous lawnmowers to powered exoskeletons and window cleaners -- are rapidly entering homes and workplaces, yet their security remains rooted in assumptions of specialized…

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external knowledge via vector similarity search. Nevertheless, these systems encounter a significant…

The agent--tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks typically function at the user-prompt or retrieval-augmented generation (RAG) context layer…

This study presents a Secure Multi-Tenant Architecture (SMTA) combined with a novel concept Burn-After-Use (BAU) mechanism for enterprise LLM environments to effectively prevent data leakage. As institutions increasingly adopt LLMs across…

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…

Graph-structured datasets are increasingly central to sensitive applications spanning social networks, biomedical research, and cryptographic systems. As organizations share these datasets with trusted parties for collaborative analysis,…

Backdoor watermarking has emerged as the predominant approach for protecting public datasets, enabling dataset ownership verification (DOV) through embedded triggers that induce predefined model behaviors. While existing works assume that…

Classical public-key cryptography standards rely on the Rivest-Shamir-Adleman (RSA) encryption protocol. The security of this protocol is based on the exponential computational complexity of the most efficient classical algorithms for…

Benchmarking presence-only passive reconnaissance in smart-grid communications is challenging because the adversary is receive-only, yet nearby observers can still alter propagation through additional shadowing and multipath that reshapes…

The rapid expansion of Internet use has increased system exposure to cyber threats, with advanced persistent threats (APTs) being especially challenging due to their stealth, prolonged duration, and multi-stage attacks targeting high-value…

Outsourcing encrypted data to the cloud creates a fundamental tension between data privacy and functional searchability. Current Searchable Symmetric Encryption (SSE) solutions frequently have significant limitations, such as excessive…