cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5441, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

26
Network-Exposed Configuration Attacks on LLM-Controlled Social Robots
📄 Paper arXiv cs.CR 23 giờ trước

arXiv:2611.22761v1 Announce Type: new Abstract: Large language models (LLMs) in embodied robots create security dependencies beyond inference. We investigate a network-exposed configuration attack on the Pollen Robotics Reachy Mini Lite, allowing an unauthenticated attacker to r…

🅲 hạng C
26
Weight-Space Programming Doesn't Need Transformers
📄 Paper HF Daily Papers 2 ngày trước

Standard neural architectures such as the Transformer were chosen because they train well with gradient descent and run fast on GPUs. In weight-space programming, a large language model (LLM) writes target weights by hand without gradient-based training, so those reasons no longe…

🅲 hạng C
26
Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core
📄 Paper arXiv cs.AI 27 ngày trước

Steward là hệ thống multi-agent LLM có lõi an toàn bất biến (invariant core) dùng cho đầu tư tự động, kết hợp 9 agent chuyên môn phân tích dữ liệu Web để thực hiện giao dịch mà vẫn đảm bảo các rào chắn bảo mật và kiểm soát rủi ro.

🅲 hạng C
26
CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference
📄 Paper HF Daily Papers 2 ngày trước

CAD practitioners often work with proprietary parts that they are unwilling to share with external services. For individuals and small companies, bringing this work in-house also requires computational resources they can afford. We introduce CADMAGEDDON, an open-source agent that…

🅲 hạng C
26
Agents Cannot Hand Over What They Have Not Yet Understood
📄 Paper arXiv cs.AI 1 ngày trước

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 …

🅲 hạng C
26
SPLICE: Structured Prompt Local Iterative Combinatorial Evolution
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.18883v1 Announce Type: new Abstract: Natural language optimization (NLO) improves an agent by having a model critique and rewrite its natural language policy parameters: system prompts, tool instructions, reasoning directives, few-shot demonstrations. These artifacts …

🅲 hạng C
26
FundingClaw: Automated Grant Proposal Writing Agents System
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.19157v1 Announce Type: new Abstract: Grant proposal writing remains a manual, labor-intensive bottleneck: proposals must satisfy rigid, agency-specific templates, and the same intellectual content must be repeatedly re-encoded into incompatible formats across funding …

🅲 hạng C
26
HalluProbe: Exploiting VLM Hallucinations for Backdoor Detection
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.19868v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are vulnerable to backdoor attacks introduced through data poisoning, making effective backdoor detection a critical security challenge. In this paper, we uncover a novel connection between VLM halluci…

🅲 hạng C
25
Where Autonomy Belongs: A Separation of Powers for Agentic Program Evolution
📄 Paper arXiv cs.AI 5 ngày trước

Paper đề xuất 'tách quyền lực' (separation of powers) cho agentic program evolution với 3 vai trò: govern (điều hướng từ bằng chứng), propose (sinh ứng viên), judge (validate fitness). Thống kê thấy hệ thống controller-centric và agent-centric đều lệch bên và tổn phí tài nguyên khi agent tự làm cả hai. Tham khảo khi design kiến trúc evolution pipeline cho code agent.

🅲 hạng C
25
AI Reviews Are Biased Towards the Appendix
📄 Paper HF Daily Papers 6 ngày trước

Large language models (LLMs) are increasingly used by reviewers to highlight weaknesses during the reviewing process, and their outputs often shape the reviews that humans submit. Prior work studies how LLM reviews align with human ones, yet we know little about which parts of a …

🅲 hạng C
25
Sign Here: Attributing a Source for a More Trustworthy Software Supply Chain
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.28794v1 Announce Type: new Abstract: Software supply chain attacks continue to be on the rise, exploiting the trust that helps open source ecosystems thrive. Recent incidents like the Shai-Hulud worm and the Axios compromise demonstrate that a single malicious package…

🅲 hạng C
👁 Trúng danh sách theo dõi: kw:supply chain
25
AIRO: A Streaming-Based Machine Learning Framework for Threat Detection and Security in Industrial Internet of Things
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30713v1 Announce Type: new Abstract: Modern Industrial Internet of Things (IIoT) im- plementations now connect edge gateways, cloud dashboards and business applications. This improves visibility and remote monitoring. However it simultaneously exposes industrial traff…

🅲 hạng C
25
Automated Post-Exploitation Attack Chain Exploration Based on a Phase-guided Hybrid Planning-Monte Carlo Tree Search Algorithm
📄 Paper arXiv cs.CR 24 ngày trước

arXiv:2610.32278v1 Announce Type: new Abstract: Advanced attackers in post-exploitation scenarios increasingly craft attack chains that combine benign operations, configuration errors, and vulnerability exploitation to achieve objectives like privilege escalation. While such cha…

🅲 hạng C
25
Post-Training Large Language Models with LLMON
📄 Paper arXiv cs.AI 20 ngày trước

arXiv:2610.38120v1 Announce Type: new Abstract: Large Language Models (LLMs) treat all context tokens uniformly, lacking explicit separation between executable instructions and passive data. This leads to prompt injection vulnerabilities, ambiguous instruction binding, and unrel…

🅲 hạng C
25
RiskyPy: Toward Model-Calibrated Prompt Generation for Joint Security and Functionality Evaluation of LLM-Generated Code
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2610.40735v1 Announce Type: new Abstract: Evaluating approaches that improve the security of LLM code generation requires datasets that jointly assess security and functionality and remain adapted to the capabilities of the models being studied. However, existing benchmark…

🅲 hạng C
25
Counterexample-driven autonomous research with application to excess radiated energy in a Z-pinch
📄 Paper arXiv cs.AI 14 ngày trước

arXiv:2611.03721v1 Announce Type: new Abstract: Recent breakthroughs in artificial-intelligence-assisted mathematics show that open-ended machine search can outperform human mathematicians, yet transferring this paradigm to physics requires refactoring the research workflow. We …

🅲 hạng C
25
Towards Early Warning of Real-World Vulnerabilities: An Evidence-Aware Decoupled Method for CVSS Vector Prediction Based on Unstructured Disclosures
📄 Paper arXiv cs.CR 13 ngày trước

arXiv:2611.06477v1 Announce Type: new Abstract: Early assessment of Common Vulnerability Scoring System (CVSS) vectors from Open Source Intelligence (OSINT) can reduce the delay between initial public disclosure and official National Vulnerability Database (NVD) scoring. Existin…

🅲 hạng C