arXiv:2611.20514v1 Announce Type: new Abstract: Replaying a vulnerability's original proof-of-concept after patching tests whether its reported trigger remains reproducible, but does not establish that the underlying security invariant holds on other code paths. We present a ben…
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5352, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.19295v1 Announce Type: new Abstract: Deception (honeypots, decoys and canary credentials) rests on a simple premise: legitimate users never touch a fake asset, so any touch is a high-confidence signal. We ask whether that premise holds when the attacker is a large lan…
arXiv:2611.19886v1 Announce Type: new Abstract: Large Language Model (LLM) agents interact with their environments through tools, reading repositories, running builds, and pushing code. When a tool fails with an ordinary error, such as a rate limit or a timeout, the agent can fa…
arXiv:2611.17639v1 Announce Type: new Abstract: Before an LLM agent cancels a reservation or deletes a folder for a user, what stops it from acting on a false assumption: what its tools show, or what the user says? In this work, we study this gap with presupposition theory from …
arXiv:2611.18642v1 Announce Type: new Abstract: Agents that work beyond a single context window, or in teams, hand their work to a successor as a short written summary. Evaluation has focused on whether an agent can solve a task, and relatively little is known about how much of …
arXiv:2611.19227v1 Announce Type: new Abstract: Task configurations in factories, warehouses, and everyday physical environments change over time. Physical AI systems therefore need to incorporate new facts into scene memory while preserving valid information about equipment, ob…
arXiv:2611.19551v1 Announce Type: new Abstract: Payment operations requested by an AI agent may remain executable, or their outcomes unresolved, after the agent has stopped. We study when a trusted payment service can account for every payment in an epoch and exclude further pay…
A security research case study on how missing authentication in Mobile MCP exposed Android screen data and device-control functionality. Continue reading on Medium »
arXiv:2611.17610v1 Announce Type: new Abstract: Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This practice confounds coordination with sample multiplicity and inference compute. We synthesize nine primary empi…
arXiv:2611.17395v1 Announce Type: new Abstract: Recent advances in weight-space programming (WSP) have demonstrated that large language models (LLMs) can directly inspect and modify neural network weights without conventional gradient-based training. While this capability opens …
🧩 Chức năng: Tự động hoá quy trình
Repo cung cấp bộ environment suite dành cho Claude AI pipeline management và custom automation workflows, có tên jailbreak-prompt – có thể dùng để thử thách bảo mật AI, study prompt injection hoặc red-teaming Claude.
arXiv:2611.13217v1 Announce Type: new Abstract: This study examines the reliability of Claude Code, an agentic deployment of the Claude Opus 4.6 large language model, as a grading system for handwritten university exams. Four research questions addressed agreement with expert hu…
arXiv:2611.17616v1 Announce Type: new Abstract: Behavioral clusters learned over user or item interactions drift as behavior evolves: some fragment into sub-behaviors, some converge, some disappear, and new patterns emerge. Two paradigms dominate the maintenance of evolving clus…
arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…
arXiv:2611.19082v1 Announce Type: new Abstract: The objective of this study is to investigate the role of clinical variables - their breadth, source, and quality - in the development, utility, and generalisability of an AI system for bi-parametric MRI (bpMRI)-based diagnosis of …
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:2611.20115v1 Announce Type: new Abstract: Advancements in artificial intelligence (AI) have accelerated digital content generation and intensified concerns around fraud, misuse, counterfeiting, and content provenance. Defensive image watermarking provides a practical mecha…
arXiv:2611.20583v1 Announce Type: new Abstract: AI-assisted security systems can recommend rapid policy changes, but governing their execution requires explicit authorization, evidence, and recovery rules. This study evaluated a machine-verifiable, state-machine-governed transit…
arXiv:2611.20594v1 Announce Type: new Abstract: An enterprise breach causes most of its damage after the perimeter is crossed. Once an attacker gains a foothold, they can move laterally to other hosts, take over the trusted services of the network, and encrypt the backups needed…
A Stripe auth bypass let a locked, timed-out dashboard still invite a new admin. Why client-side lockouts fail and the server-side fixes. Continue reading on Medium »
🎯 Kẻ tấn công làm gì (từng bước)
- Tìm endpoint/API không kiểm tra đăng nhập hoặc kiểm tra sai
- Gọi thẳng API quản trị/người dùng khác mà không cần mật khẩu
- Dùng được toàn bộ chức năng với quyền cao
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Request tới API quản trị mà không có cookie/token
- Truy cập 200 vào đường dẫn yêu cầu đăng nhập
- Một IP lạ gọi hàng loạt API quản trị
🛡 Phòng ngay (làm được hôm nay)
- Vá ngay
- Kiểm tra lại toàn bộ route quản trị có middleware xác thực
- Chặn /admin, /api/admin ở reverse proxy nếu không dùng từ ngoài
Facebook IDOR let users delete any visible album via the Graph API. How the missing ownership check worked, impact, and API fixes. Continue reading on Medium »
arXiv:2611.14864v1 Announce Type: new Abstract: An AI agent's decision not to act can itself become an attack surface. We study warning-induced over-abstention, an availability attack in which adversaries place fabricated risk warnings in low-trust content to prevent legitimate …
Fossil fuels are still the biggest source of electricity for hyperscale data centers in the US, a new paper published in the journal Nature Sustainability shows. They likely burn through more electricity collectively than many countries do, resulting in a serious amount of greenh…
Artificial intelligence is changing how financial information is collected, processed, and interpreted. Traditional market research often involves reviewing charts, comparing indicators, studying financial news, and monitoring price movements manually. AI-assisted technology can …
arXiv:2611.14997v1 Announce Type: new Abstract: When people face a hard problem, they often restate it in a clearer way before solving it. We study whether the same habit helps large language models by rewriting the statement of a problem. A legal rewrite must keep the meaning, …
arXiv:2611.15102v1 Announce Type: new Abstract: LLMs are increasingly used for forecasting, and the best forecasting systems retrieve news as evidence to strengthen their predictions. This also opens them to attack. We study the weakest attacker of this kind, who knows only the …
arXiv:2611.17796v1 Announce Type: new Abstract: Daily GPU rental-price benchmarks can fail when marketplace quotes are missing. This article stress-tests a fixed equal-weight median rule under four imposed masking mechanisms and four benchmark-level recovery methods. Across 5,80…
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:2611.17646v1 Announce Type: new Abstract: Weightless Neural Networks (WNNs) are lightweight classifiers that binarize their inputs and learn by storing binary patterns in lookup memories, which makes them attractive for resource-constrained tasks such as intrusion detectio…
arXiv:2611.17907v1 Announce Type: new Abstract: We consider a physical layer authentication scenario in which a legitimate user (Alice) communicates with an authenticator (Bob) through a reconfigurable intelligent surface (RIS), controlled by Bob. An attacker (Trudy) aims to imp…
arXiv:2611.17684v1 Announce Type: cross Abstract: Adversarial training is a common technique for making neural networks more robust to small, intentionally crafted input perturbations, and robustness is commonly measured through accuracy under attack. By exploring inter-network …
arXiv:2611.18358v1 Announce Type: cross Abstract: Almost perfect nonlinear (APN) functions of $\mathbb{F}_2^n$ have the lowest possible differential uniformity. The only known APN permutation in even dimension, in dimension six, is equivalent to a quadratic APN function with a n…
arXiv:2611.18563v1 Announce Type: cross Abstract: Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification Syste…
arXiv:2611.14164v1 Announce Type: new Abstract: Vulnerabilities in applications, including browsers, media players, online services and document readers, etc. are often exploited and cause a serious damage. The vulnerabilities could exist in your system maybe because of some cod…
Apple's new app for a study will answer everyday medical questions
Apple announced a new study today with the goal of better understanding how people interact with conversational AI health tools and how useful their responses actually are. The company is conducting the Apple Health AI Usage Study in collaboration with OpenEvidence, a clinical AI…
Speculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block in a single forward pass, but mainly focus on text-only tasks, leaving multimod…
Underwater image enhancement is challenging to evaluate due to the lack of clean reference images, so researchers rely on no-reference image quality assessment (NR-IQA) metrics. However, it remains unclear whether these metrics agree with human judgments. We evaluate 73 handcraft…
While testing a profile picture upload feature on a web application, one simple question came to mind: “Does the server actually validate… Continue reading on Medium »
🎯 Kẻ tấn công làm gì (từng bước)
- Chưa đủ dữ liệu để mô tả phương thức — cần đọc mô tả gốc hoặc tra NVD
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
- Không xác định được từ dữ liệu hiện có
🛡 Phòng ngay (làm được hôm nay)
- Cập nhật thành phần liên quan tới mức mới nhất
- Theo dõi NVD/CVE để có mô tả đầy đủ
arXiv:2611.14736v1 Announce Type: new Abstract: Observational causal discovery often leaves causal di- rections unresolved or unstable. Large language mod- els (LLMs) can provide semantic information to resolve these directions, but incorrect proposals can exclude the true causa…