密码学与安全

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…

Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful…

RAG has emerged as a key technique for enhancing response quality of LLMs without high computational cost. In traditional architectures, RAG services are provided by a single entity that hosts the dataset within a trusted local environment.…

Traditional side-channels take advantage of secrets being used as inputs to unsafe instructions, used for memory accesses, or used in control flow decisions. Constant-time programming, which restricts such code patterns, has been widely…

Analysis of clinical data is a cornerstone of biomedical research with applications in areas such as genomic testing and response characterization of therapeutic drugs. Maintaining strict privacy controls is essential because such data…

Personalized health analytics increasingly rely on population benchmarks to provide contextual insights such as ''How do I compare to others like me?'' However, cohort-based aggregation of health data introduces nontrivial privacy risks,…

Visual token compression is widely adopted to improve the inference efficiency of Large Vision-Language Models (LVLMs), enabling their deployment in latency-sensitive and resource-constrained scenarios. However, existing work has mainly…

Intrusion detection systems (IDS) are essential for protecting computer systems and networks against a wide range of cyber threats that continue to evolve over time. IDS are commonly categorized into two main types, each with its own…

NoSQL Injection attacks are a class of cybersecurity attacks where an attacker sends a specifically engineered query to a NoSQL database which then performs an unauthorized operation. To defend against such attacks, rule based systems were…

Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based attacks that exploit over-privileged tool use. This paper aims to understand and mitigate…

The Instruction Set Architecture (ISA) defines processor operations and serves as the interface between hardware and software. As an open ISA, RISC-V lowers the barriers to processor design and encourages widespread adoption, but also…

We present the first comprehensive analysis of ARM MTE hardware performance on four different microarchitectures: ARM Big (A7x), Little (A5x), and Performance (Cortex-X) cores on the Google Pixel 8 and Pixel 9, and on Ampere Computing's…

We develop DroidCCT, a distributed test framework to evaluate the scale of a wide range of failures/bugs in cryptography for end users. DroidCCT relies on passive analysis of artifacts from the execution of cryptographic operations in the…

An extensive line of work on modern computing architectures has shown that the execution time of instructions can (i) depend on the operand of the instruction or (ii) be influenced by system optimizations, e.g., branch prediction and…

The fine-tuning technique in deep learning gives rise to an emerging lineage relationship among models. This lineage provides a promising perspective for addressing security concerns such as unauthorized model redistribution and false claim…

Modern digital ecosystems, spanning software, hardware, learning models, datasets, and cryptographic products, continue to grow in complexity, making it difficult for organizations to understand and manage component dependencies. Bills of…

Serverless computing has achieved widespread adoption, with over 70% of AWS organizations using serverless solutions [1]. Meanwhile, machine learning inference workloads increasingly migrate to Function-as-a-Service (FaaS) platforms for…

We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate at watermarking LM outputs for constrained generation tasks with low-entropy output spaces.…

This paper focuses on solving unconstrained privacy-preserving black-box optimization (PBBO), its corresponding least Frobenius norm updating of quadratic models, and the differentially privacy mechanisms for PBBO. Optimization problems…

Certified deletion allows Alice to outsource data to Bob and, at a later time, obtain a verifiable guarantee that the file has been irreversibly deleted at her request. The functionality, while impossible using classical information alone,…