arXiv:2611.22223v1 Announce Type: new Abstract: Large Language Model (LLM)-based web agents rely on data minimization and least privilege to protect user privacy. We show that these principles are necessary but insufficient: they constrain authorized sources, but not higher-sens…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5461, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.20223v1 Announce Type: new Abstract: Artificial intelligence is increasingly integrated into healthcare systems, from clinical information retrieval to workflow automation and decision support, which introduces new security, privacy, and trust risks with direct implic…
1.16.0
API phân quyền của Gitea không kiểm tra chặt chẽ, cho phép bất kỳ người dùng đã đăng nhập nào cũng có thể tra cứu vai trò ẩn của người dùng khác trong các tổ chức công khai hoặc giới hạn.
🎯 Kẻ tấn công làm gì (từng bước)
- Khai thác endpoint trả về quá nhiều (stack trace, danh sách user, phiên bản)
- Thu thập thông tin để chọn đòn tấn công tiếp
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Response chứa stack trace, đường dẫn nội bộ, phiên bản phần mềm
- Dò hàng loạt đường dẫn (.git, .env, backup)
🛡 Phòng ngay (làm được hôm nay)
- Tắt hiển thị lỗi ra ngoài (debug=false)
- Chặn .git/.env/backup ở web server
- Vá thành phần bị lỗi
Nền tảng Lovable bị phát hiện lỗ hổng nghiêm trọng làm lộ thông tin cá nhân như hộ chiếu và hàng trăm nghìn tin nhắn riêng tư. Đây là một bài học đắt giá về kiểm soát quyền truy cập và bảo mật dữ liệu trên các ứng dụng SaaS.
arXiv:2611.21932v1 Announce Type: cross Abstract: This study proposes an interesting approach for vehicle-to-vehicle (V2V) communication, which integrates blockchain technology, federated learning (FL), and allocation optimization of latency and resources. The research evaluates…
arXiv:2611.20389v1 Announce Type: new Abstract: Execution traces help diagnose AI-agent failures, but sharing them can expose customer identities. For example, detecting that an agent handled the wrong customer's records requires knowing whether the records belong to the request…
Proton's new Lumo Desktop app for Windows, Mac, and Linux lets users automate tasks across files and connected apps, with granular controls over what its AI can access.
arXiv:2611.18925v1 Announce Type: new Abstract: We propose a privacy-preserving selection layer for collaborative population stratification workflows, enabling an honest-but-curious server to recommend a strong clustering algorithm-hyperparameter configuration from privacy prote…
EFF đang vận động tòa án yêu cầu cảnh sát phải có lệnh khám xét mới được truy cập dữ liệu từ hệ thống nhận diện biển số xe tự động (ALPR). Đây là bước đi quan trọng trong việc bảo vệ quyền riêng tư cá nhân trước sự giám sát kỹ thuật số diện rộng.
🧩 Chức năng: Máy chủ MCP — nối công cụ/dữ liệu của bạn vào AI agent
Yogurt là một công cụ mã nguồn mở giúp xử lý ghi chú cuộc họp bằng AI hoàn toàn riêng tư. Phù hợp cho những ai muốn tự lưu trữ (self-host) để đảm bảo bảo mật dữ liệu họp hành.
iVerify Basic is a mobile security app for individuals who want to check their devices for signs of compromise and improve their security settings. It is available for iOS and Android, including tablets. Device security checks The Device tab puts scan controls and security status…
How a login-flow duplicate check ignored discoverability settings and mapped phone numbers and emails to accounts, for a $5,040 bounty Continue reading on Medium »
arXiv:2611.21694v1 Announce Type: cross Abstract: Transmitting an electrocardiogram (ECG) waveform can expose demographic information beyond an intended diagnostic task. We evaluate TIBECG, an architectural temporal information bottleneck, on individual leads extracted from hosp…
arXiv:2611.21923v1 Announce Type: cross Abstract: Published face-privacy methods report protection above 90% against black-box recognition models. That number comes from an evaluation protocol with two independent defects, reported in a measure that cannot size either one. The i…
Meta tiếp tục bị phạt 887 triệu USD tại Ý vì cách thức xử lý và truy cập dữ liệu người dùng Android trái phép. Vụ việc phản ánh rủi ro pháp lý lớn đối với các công ty thu thập dữ liệu người dùng.
Bài viết phân tích nỗ lực của các ông lớn công nghệ trong việc định nghĩa lại khái niệm quyền riêng tư nhằm phục vụ lợi ích thương mại. Đáng chú ý cho những ai quan tâm đến chính sách công nghệ và đạo đức dữ liệu.
arXiv:2611.15097v1 Announce Type: new Abstract: Web agents need to use private context without unnecessarily disclosing it. Effective protection must distinguish between requests that may be sent after sanitization and those that must be withheld, while preserving the informatio…
United says it won't let personal AI assistants book tickets on the airline, citing both privacy and regulatory concerns. The company says it hasn't yet seen many people try to use AI agents to book their flights, The Wall Street Journal reports, in line with observations from ot…
arXiv:2611.16048v1 Announce Type: new Abstract: Personalized LLM services place private facts and application instructions into a prompt, then retain representations of that context for later inference. Latent-state LLMs compress part of this history into fixed-size recurrent st…
arXiv:2611.18909v1 Announce Type: new Abstract: Genomic data sharing is essential for biomedical research but introduces significant privacy risks, including membership inference attacks, in which an adversary determines whether a specific individual's data was used in a study. …
arXiv:2611.19435v1 Announce Type: new Abstract: E-Government platforms, such as government credit platforms, handle highly sensitive personal data, requiring stringent security authentication (e.g., facial recognition, multi-factor verification) that protects users but impedes t…
arXiv:2611.17722v1 Announce Type: new Abstract: Multi-level learning/optimization, e.g., bilevel optimization, has been recognized for its versatile applicability across a broad array of domains, spanning from signal processing to machine learning. However, most existing works f…
arXiv:2611.17728v1 Announce Type: new Abstract: Model merging constructs multi-task models without expensive joint training but often suffers from parameter interference. Some solutions mitigate this by constraining finetuning using data from the other tasks to be merged, violat…
arXiv:2611.17554v1 Announce Type: new Abstract: We study private online allocation problems, where allocation decisions must satisfy differential privacy (DP) to protect sensitive user information while optimizing performance under limited resources. We first formalize different…
arXiv:2611.17596v1 Announce Type: new Abstract: Evaluating tight Differential Privacy (DP) parameters for DP matrix factorization with privacy amplification by sampling requires analyzing high-dimensional, correlated Gaussian mixtures. Because integrating these mixture distribut…
arXiv:2611.17703v1 Announce Type: new Abstract: Healthcare organizations collect huge amounts of patient data from clinical records, medical tests, monitoring systems, and healthcare services. Such data can underpin intelligent healthcare analytics but remains distributed across…
arXiv:2611.18293v1 Announce Type: new Abstract: Coding agents increasingly review code, yet whether they catch the privacy defects that laws such as the GDPR require software to avoid remains largely untested, partly because few datasets connect real privacy defects to their acc…
arXiv:2611.18312v1 Announce Type: new Abstract: Inertial sensors of smartphones are a well-known privacy risk, as they allow inferring sensitive user movements and activity without explicit permissions. Among these sensors, the magnetometer has received little attention, as it i…
arXiv:2611.18442v1 Announce Type: new Abstract: Open driving releases and usage-based insurance programs often claim to prevent privacy breaches by omitting GPS records when sharing or collecting vehicle data. However, removing GPS coordinates from driving logs does not erase th…
arXiv:2603.10099v2 Announce Type: replace-cross Abstract: The 2020 United States Census adopted differential privacy to protect individual confidentiality, adding calibrated noise to summary demographic measurements that are then reconciled into population tables. We developed B…
The directive protects smartphones as part of a person’s private sphere and requires “free and informed consent” for such access, the authority said. The post Meta Fined $887 Million in Italy Over Android Gallery Photos and Videos on Facebook appeared first on SecurityWeek .
Open driving releases and usage-based insurance programs often claim to prevent privacy breaches by omitting GPS records when sharing or collecting vehicle data. However, removing GPS coordinates from driving logs does not erase the location information carried by vehicle signals…
arXiv:2611.15373v1 Announce Type: new Abstract: Data Value Assessment (DVA) plays a critical role in modern data markets by enabling buyers to evaluate how a seller's data would improve model performance before purchase. However, existing DVA approaches require one party to reve…
arXiv:2611.16244v1 Announce Type: new Abstract: We introduce SEC, an expander-code-based ramp secret sharing scheme over $\mathbb{Z}$-modules, particularly suitable for lattice-based distributed cryptography. It is everywhere-short: bounded secret coefficients yield bounded shar…
arXiv:2611.16495v1 Announce Type: new Abstract: We implement privacy-preserving local electricity exchanges using an automated market maker on the Hyperledger Besu network under QBFT consensus. The proposed protocol operator collects individual electricity positions off-chain an…