密码学与安全

Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned…

Software practitioners use online forums to navigate complex and often ambiguous legal privacy requirements, yet little is known about their professional backgrounds, what challenges they face, and how they use and assess the credibility of…

In recent work it has been shown that colluding AI agents can use steganographic methods to exchange malicious information. Whether a transformer can implement steganographic methods depends on what cryptographic functions it can implement,…

LLM agents carry conclusions across steps and sessions in compressed memory, and memory products (e.g., mem0, LangMem) rewrite conversation into stored "facts" that later steps trust. We show this rewriting manufactures confidence: across…

Model quantization is a key technique for reducing storage and inference costs when deploying large language models in practice. However, recent studies show that the discretization and rounding errors introduced by quantization can be…

Symbolic execution is a powerful program analysis technique with broad applications, such as vulnerability detection, security testing, and malware analysis. However, this technique is known to suffer from scalability issues, e.g., path…

Text-based CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) have traditionally been a simple, affordable, lightweight, yet very effective security mechanism to distinguish human users from automated bots…

Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transports. As agents move from connection to execution, security decisions often remain split…

This paper presents new results and breakthrough obtained with the HbHAI techniques (Hash-based Homomorphic Artificial Intelligence) proposed in \cite{filiol0,sepp}. HbHAI is based on a novel class of key-dependent hash functions that…

The film 'Her' pictured a future of love between humans and AI. That future has quietly emerged in the form of Role-play AI Companions (RACs), where emotionally responsive interactions blur the boundary between tool use and relational…

Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks. In these attacks, malicious behaviors remain dormant in…

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate processes as ``agents.'' Cybersecurity workflows require…

Firmware lies at the heart of IoT devices. Its development depends heavily on third-party libraries (TPLs), which greatly accelerate the process but simultaneously introduce associated vulnerabilities. Binary Code Similarity Detection…

Detection engineering and digital forensics have evolved in parallel rather than in partnership, leaving a gap between real-time alerting and forensic analysis. This paper develops a unified detection-forensics methodology using…

AI agent protocols define how agents use tools, delegate work, and coordinate across software systems, but their security requirements remain incomplete and inconsistently enforced across deployments. We present AgentThread, a source-linked…

Tool-using LLM agents increasingly read untrusted content while holding side-effecting tools such as payments, email, CRM, and infrastructure APIs, yet common framework defaults still conflate tool exposure with authorization. We audit…

Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary…

We present RIPA, the first systematic multi-channel empirical study of prompt injection attacks delivered through the sensory pipeline of a ROS 2-based LLM-controlled robotic system. Across 100 independent runs per injection variant on five…

Connected Vehicles (CVs) rely extensively on communication technologies to enable data-driven predictive analyses for enhancing performance and safety. These communication channels can be exploited by adversaries to launch cyberattacks such…

CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD. We present the first empirical study of how DP…