密码学与安全
The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks. While this paradigm shift enhances personalization, it…
AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls -- privileged operations with side effects on shared state -- yet today's safety…
Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network…
Timing side-channel attacks exploit variations in program execution time to recover sensitive information. Cryptographic implementations are especially vulnerable to these attacks, since even small timing differences in operations such as…
Academic examination systems worldwide continue to rely on centralised, opaque record-keeping that is often vulnerable to credential forgery, result tampering, examiner bias, and the absence of transparent re-evaluation pathways. Existing…
Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods…
Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding…
Ransomware detection systems increasingly rely on behavior-based machine learning to address evolving attack strategies. However, emerging privacy compliance, data governance, and responsible AI deployment demand not only accurate detection…
As Cyber-Physical Systems (CPS) become increasingly pervasive and autonomous, ensuring the resilience of their embedded logic is critical to maintaining safety and integrity. Among the most stealthy and damaging threats are non-invasive…
Large language models write production code, and yet they routinely introduce well-known vulnerabilities. We show that this is not a knowledge deficit: the same models that generate insecure code, correctly identify and explain the…
The modern cryptographic primitives are known to generate large volumes of sequential data like keystreams, ciphertext blocks, and hash outputs. Traditional cryptgraphic evaluation methods rely primarily on statistical randomness tests and…
Prior work shows that fine-tuning aligned models on benign data degrades safety in text and vision modalities, and that proximity to harmful content in representation space predicts which samples cause the most damage. However, existing…
Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…
Light clients are essential for scalable blockchain systems because they verify data availability without downloading full blocks. In data availability sampling based systems, sampled cells are retrieved from a peer-to-peer network and…
Research on large language model (LLM) security is shifting from "will the model leak training data" to a more consequential question: can an agent with persistent, long-term memory be continuously shaped, cross-session poisoned, accessed…
Safety guardrails have become an active area of research in AI safety, aimed at ensuring the appropriate behavior of large language models (LLMs). However, existing research lacks consideration of nuances across linguistic and cultural…
The communication protocols and data transfer mechanisms employed by IoT devices in smart buildings and corresponding digital twin systems predominantly rely on centralized architectures. Such centralized systems are vulnerable to single…
As autonomous AI agents increasingly call other agents to complete tasks on behalf of a human principal, a structural accountability gap has emerged: the calling agent accepts the terms of service of the callee without any protocol-level…
The deployment of Large Language Models in agentic, multi-turn conversational settings has introduced a class of privacy vulnerabilities that existing protection mechanisms are not designed to address. Current approaches to Personally…
Cashback reward programs now serve as central instruments in the competitive landscape of cards, digital wallets, and payment platforms. Despite their financial significance, the business logic governing these programs is seldom treated as…