密码学与安全

5G Core networks are entering a decisive phase of post-quantum (PQ) migration: operators and vendors are beginning to advertise PQ-TLS 1.3, PQ-IPsec, and hybrid KEM support across the Service-Based Interface (SBI) and N2, N3, N4 reference…

Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is highly vulnerable to imperceptible perturbations as a…

Collaborative perception allows connected and autonomous vehicles (CAVs) to improve perception by sharing sensory data, but it also introduces security risks from manipulated inputs. Prior work shows that attackers can spoof or remove…

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…

AI browsing agents are an emerging class of AI-powered bots capable of autonomously navigating websites. Unlike traditional web bots, AI browsing agents typically operate using real browsers and perform everyday tasks, making them difficult…

Account-based ledgers -- standard externally-owned accounts (EOAs), ERC-4337 smart accounts, post-Pectra EIP-7702 delegated EOAs -- place the holder of the controlling key at the apex of asset authorization. We ask a structural question…

Blockchain and decentralized finance have revolutionized the financial ecosystem while simultaneously exposing it to cryptocurrency phishing attacks. Existing phishing detection methods primarily rely on graph learning, but they face…

In this paper, we propose a method for privacy-preserving federated learning that uses randomly selected model parameters to update global models. High-quality deep neural networks (DNN) models require a huge amount of training data in…

AI-driven penetration testing agents are now capable of autonomously executing attacks within compromised networks. Identifying the model family that controls the active sessions of such agents provides valuable information towards…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Machine unlearning (MU) has emerged as a key mechanism for ensuring data privacy and regulatory compliance by enabling models to forget specific training samples. However, recent studies have shown that the removal of data can inadvertently…

Retrieval-augmented generation and tool-integrated LLM agents increasingly depend on external textual sources. This reliance broadens the available attack surface, allowing adversaries to insert malicious instructions that trigger…

Hallucinations, outputs that sound plausible but are factually incorrect, remain an open challenge for deployed LLMs. In code generation, models frequently hallucinate non-existent software packages, recommending imports and installation…

LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks that elicit harmful behaviors without explicit policy violations. While a growing body of…

We develop a unified mathematical formulation for post-quantum authenticated telemetry and actuation in FADEC-coupled dual-spool turbofan cyber-physical systems. The formulation integrates lattice-based key establishment under LWE/SIS-style…

Retrieval-Augmented Generation (RAG) equips large language models (LLMs) with external evidence by retrieving documents at inference time, but it also turns the retrieval corpusinto a sensitive asset. Under a black-box setting, an adversary…

As large language models are integrated into autonomous robotic systems for task planning and control, compromised inputs or unsafe model outputs can propagate through the planning pipeline to physical-world consequences. Although prior…

Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential…

Private information retrieval (PIR) allows private database queries; however, it is hindered by intense server-side computation and memory traffic. Numerous modern lattice-based PIR protocols consist of three phases: ExpandQuery (expanding…

Centralized stablecoins such as USDT and USDC enforce sanctions through contract-layer blacklist functions. Yet on public blockchains, a freeze is still an ordinary transaction competing with the sanctioned party's transfer for priority. It…