密码学与安全

Graph-structured data underpin a wide spectrum of modern applications. However, complex graph topologies and homophilic patterns can facilitate attribute inference attacks (AIAs) by enabling sensitive information leakage to propagate across…

Large Language Models (LLMs) have demonstrated remarkable proficiency in vulnerability detection. However, a critical reliability gap persists: models frequently yield correct detection verdicts based on hallucinated logic or superficial…

Random Access Channel (RACH) jamming poses a critical security threat to 5G and beyond (B5G) networks. This paper presents an analytical model for predicting the impact of Msg1 jamming attacks on RACH performance. We use the…

Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation…

Retrieval-augmented generation (RAG) is increasingly deployed in real-world applications, where its reference-grounded design makes outputs appear trustworthy. This trust has spurred research on poisoning attacks that craft malicious…

This paper presents a survey of state-of-the-art trust models for Vehicular Ad Hoc Networks (VANETs). Trust management plays an essential role in isolating malicious insider attacks in VANETs which traditional security approaches fail to…

Automated detection of cyber attacks is a critical capability to counteract the growing volume and sophistication of cyber attacks. However, the high numbers of security alerts issued by intrusion detection systems lead to alert fatigue…

Machine Learning (ML) models, including Large Language Models (LLMs), are characterized by a range of system-level attributes such as security and reliability. Recent studies have demonstrated that ML models are vulnerable to multiple forms…

We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or…

Graph-based retrieval-augmented generation (Graph RAG) is increasingly deployed to support LLM applications by augmenting user queries with structured knowledge retrieved from a knowledge graph. While Graph RAG improves relational…

We address the problem of runtime trajectory anomaly detection, a critical capability for enabling trustworthy LLM agents. Current safety measures predominantly focus on static input/output filtering. However, we argue that ensuring LLM…

The sharing of the last-level cache (LLC) among multiple cores makes it vulnerable to cross-core conflict- and occupancy-based attacks. Despite extensive prior work, modern processors still employ non-secure set-associative LLCs. Existing…

Multimodal large language models (MLLMs) are pushing recommender systems (RecSys) toward content-grounded retrieval and ranking via cross-modal fusion. We find that while cross-modal consensus often mitigates conventional poisoning that…

Machine learning (ML) models are increasingly deployed in cybersecurity applications such as phishing detection and network intrusion prevention. However, these models remain vulnerable to adversarial perturbations small, deliberate input…

The deployment of autonomous AI agents capable of executing commercial transactions has motivated the adoption of mandate-based payment authorization protocols, including the Universal Commerce Protocol (UCP) and the Agent Payments Protocol…

Since most countries are coming up with online privacy regulations, such as GDPR in the EU, online publishers need to find a balance between revenue from targeted advertisement and user privacy. One way to be able to still show targeted…

Understanding TTPs (Tactics, Techniques, and Procedures) in malware binaries is essential for security analysis and threat intelligence, yet remains challenging in practice. Real-world malware binaries are typically stripped of symbols,…

Biological AI tools for protein design and structure prediction are advancing rapidly, creating dual-use risks that existing safeguards cannot adequately address. Current model-level restrictions, including keyword filtering, output…

Satellite-terrestrial networks (STNs) have emerged as a promising architecture for providing seamless wireless coverage and connectivity for multiple users. However, potential malicious eavesdroppers pose a serious threat to the private…

As large language models (LLMs) evolve into autonomous agents, their real-world applicability has expanded significantly, accompanied by new security challenges. Most existing agent defense mechanisms adopt a mandatory checking paradigm, in…