相关论文: A solution for ARP spoofing: Layer-2 MAC and proto…

The evil twin attack is a major security threat to WLANs. An evil twin is a rogue AP installed by a malicious user to impersonate legitimate APs. It intends to attract victims in order to intercept their credentials, to steal their…

Deep reinforcement learning (DRL) policies are vulnerable to unauthorized replication attacks, where an adversary exploits imitation learning to reproduce target policies from observed behavior. In this paper, we propose Constrained…

Google and Apple have jointly provided an API for exposure notification in order to implement decentralized contract tracing apps using Bluetooth Low Energy, the so-called "Google/Apple Proposal", which we abbreviate by "GAP". We…

The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data sources. By defining a set of common client-server message exchange clauses, MCP replaces…

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…

Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data. While fine-tuning enhances performance by internalizing domain…

Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that…

The Model Context Protocol (MCP) has emerged as a standard for connecting large language models (LLMs) with external tools. However, this MCP ecosystem introduces new security risks across hosts, servers, and registries. In this paper, we…

Modern x86 processors support an AVX instruction set to boost performance. However, this extension may cause security issues. We discovered that there are vulnerable properties in implementing masked load/store instructions. Based on this,…

Anomaly detection has emerged as a popular technique for detecting malicious activities in local area networks (LANs). Various aspects of LAN anomaly detection have been widely studied. Nonetheless, the privacy concern about individual…

We present a systematic study of provider-side data poisoning in retrieval-augmented recommender systems (RAG-based). By modifying only a small fraction of tokens within item descriptions -- for instance, adding emotional keywords or…

A whole range of attacks becomes possible when adversaries gain physical access to computing systems that process or contain sensitive data. Examples include side-channel analysis, bus probing, device cloning, or implanting hardware…

Existing model poisoning attacks to federated learning assume that an attacker has access to a large fraction of compromised genuine clients. However, such assumption is not realistic in production federated learning systems that involve…

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

This paper proposes a robust adversarial reinforcement learning (RARL)-based multi-access point (AP) coordination method that is robust even against unexpected decentralized operations of uncoordinated APs. Multi-AP coordination is a…

In advanced metering infrastructure (AMI), smart meters (SMs), which are installed at the consumer side, send fine-grained power consumption readings periodically to the electricity utility for load monitoring and energy management. Change…

Secure communications are playing increasing roles in society, particularly in finance, journalism, and military projects. Current methods of securing e-mail and similar messaging methods rely on encryption of the message body, but the…

As Deep Packet Inspection (DPI) middleboxes become increasingly popular, a spectrum of adversarial attacks have emerged with the goal of evading such middleboxes. Many of these attacks exploit discrepancies between the middlebox network…

Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning…

We show how an off-path (spoofing-only) attacker can perform cross-site scripting (XSS), cross-site request forgery (CSRF) and site spoofing/defacement attacks, without requiring vulnerabilities in either web-browser or server and…