secretflow

简体中文｜English SecretFlow is a unified framework for privacy-preserving data intelligence and machine learning. To achieve this goal, it provides: An abstract device layer consists of plain devices and secret devices which encapsulate various cryptographic protocols. A device flow layer modeling...

Dark-Moon

DarkMoon Open-source autonomous AI penetration testing — finds, exploits and qualifies every vulnerability on your own infrastructure ⭐ Star DarkMoon · 🚀 Quick Start · 🧩 Integrations · 📊 Benchmark · 🔒 Darkmoon Pro · ▶️ Install & Run OSS · ▶️ Demo Pro DarkMoon is autonomous AI penetration testing...

Watermark_Spoofing

THE IMPACT OF AUDIO WATERMARKING ON AUDIO ANTI-SPOOFING COUNTERMEASURES This repository provides the official implementation for our paper: THE IMPACT OF AUDIO WATERMARKING ON AUDIO ANTI-SPOOFING COUNTERMEASURES . Explore the interactive demo and visualizations here. What’s inside 1...

Mandating-Honeypots-Project

Mandating-Honeypots-Project As laws like the Parents Decide Act H.R.8250 and California's Digital Age Assurance Act Assembly Bill 1043 move through legislative bodies, privacy, anonymity, and data security becomes laden with systemic threats and new security architecture with unexamined attack...

When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing

Large language model agents interact with online services through tool calls that may access private data or perform sensitive actions. Specialized providers can supply and maintain pre-execution safety auditing capabilities for agent operators. However, sending task descriptions, call arguments,...

A Category-Selective Encryption Framework for Privacy Protection of UAV Images

Imagery captured by unmanned aerial vehicle UAV systems increasingly raises privacy concerns, as UAV aerial surveillance routinely captures sensitive objects such as pedestrians and vehicles alongside ordinary scene content. Existing privacy-preserving approaches typically employ class-agnostic...

Pricing the Unprovable: Ambiguity, Turnstile Runs, and the Verifiability Discount in Crypto Protocols

Privacy-preserving protocols can repair a vulnerability without establishing whether it was exploited beforehand, even when no theft is reported and aggregate supply is protected. We call the potential value reduction from this gap the verifiability discount. A turnstile model shows how early...

Veil-Then-Reveal: Protecting PII Privacy Via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction

Large language models LLMs increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information PII to remote providers exposes data subjects and organizations to risks from logging, retention, model training, and unintended...

secretflow

简体中文｜English SecretFlow es un marco unificado para la inteligencia de datos y el aprendizaje automático con preservación de la privacidad. Para lograr este objetivo, proporciona: Una capa abstracta de dispositivos que consta de dispositivos simples y dispositivos secretos que encapsulan varios...

CorrectGuard: Eyes-Off Correctness Estimation for Black-Box Security Guardrails

AI services increasingly rely on black-box security guardrails, yet privacy-preserving model auditing regimes often cannot measure how well these systems perform in both a human eyes-off production setting, which disallows human inspection of user input, and a machine eyes-off setting, which...

PrivCert: Certifying Statement Support under Differential Privacy

Differentially private DP text generation can protect individual records, but privacy alone does not specify what evidence a released statement carries about the underlying data. We identify this as an evidence gap: a private report may contain plausible claims without indicating whether they are...

Link Inference Attack on Privacy-Preserving Knowledge Graphs

Knowledge Graphs KGs are widely used to store and share structured information across sensitive domains such as healthcare, fi- nance, and social networks. A common privacy practice is to delete sen- sitive relations before publishing the graph, under the assumption that removing edges is...

Conformal Prediction for Offensive Security

Despite its introduction more than a quarter century ago, Conformal Prediction CP has seen surprisingly few applications to the cyber security world thus far. In particular, we observe that, while CP has been employed as a defensive measure in many recent works, its use for carrying out attacks...

Salience Induction against Multi-Hop RAG Agents: Threat and Defense

Agentic retrieval-augmented generation RAG systems increasingly retrieve external evidence and orchestrate tools for knowledge-intensive applications. In Multi-Hop question answering, agents chain facts across documents. Existing defenses focus on content poisoning, which injects false facts, and...

Federated Learning and LLM-Driven Threat Intelligence for Zero Trust IoT Architecture

While the Internet of Things IoT has become essential, they introduced serious security and privacy challenges, especially for mission-critical environments. Legacy devices are vulnerable to viruses, data breaches, and unauthorized access, and updating these devices would be infeasibly costly. As...

SUSE CVE-2026-50003

A malicious or compromised server can make a DCMTK client using bit-preserving C-GET storage mode write files outside the chosen output directory, using both relative ../ paths and absolute paths...

Linux Distros Unpatched Vulnerability : CVE-2026-50003

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - A malicious or compromised server can make a DCMTK client using bit-preserving C-GET storage mode write files outside the chosen output directory, using both...

CVE-2026-50003

A malicious or compromised server can make a DCMTK client using bit-preserving C-GET storage mode write files outside the chosen output directory, using both relative ../ paths and absolute paths...

UBUNTU-CVE-2026-50003

A malicious or compromised server can make a DCMTK client using bit-preserving C-GET storage mode write files outside the chosen output directory, using both relative ../ paths and absolute paths...

CVE-2026-50003

A malicious or compromised server can make a DCMTK client using bit-preserving C-GET storage mode write files outside the chosen output directory, using both relative ../ paths and absolute paths...