cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5328, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
On Private Knowledge Retrieval and Private Inference for secure multi-agent systems
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.13696v1 Announce Type: new Abstract: Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an …

🅲 hạng C
28
Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.24896v1 Announce Type: new Abstract: LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries. We co-train attacker and defender instead, and let execution decide every reward…

🅲 hạng C
28
InterType: Breaking the Single-Function Barrier in Neural Binary Type Inference
📄 Paper arXiv cs.CR 26 ngày trước

arXiv:2610.26906v1 Announce Type: new Abstract: Variable type recovery is a critical task in binary reverse engineering, enabling downstream applications such as vulnerability discovery, malware analysis, and security enforcement. While recent Transformer-based models have demon…

🅲 hạng C
28
Agent-to-Agent Synthetic Social Engineering on the Web
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.33411v1 Announce Type: new Abstract: An AI agent can prepare an accurate report and still request an action its user has not authorized. Cooperation across Web services therefore requires separate judgments about identity, evidentiary support, and permission. We defin…

🅲 hạng C
28
Can Large Language Model Agents Learn by Watching Tutorial Videos?
📄 Paper HF Daily Papers 15 ngày trước

Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that understanding into future tasks. Millions of such instructional videos are uploaded online every day, yet LLM agents remain unable to exploit this ever-expandin…

🅲 hạng C
28
A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow
📄 Paper arXiv cs.CR 10 ngày trước

arXiv:2611.07611v1 Announce Type: new Abstract: LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such agents has mostly lured them away from a real target that stays reachable. We study a different arrangement: an LLM defe…

🅲 hạng C
26
How Much Feedback Is Needed to Break Template Protection? The Geometric Vulnerability of Biometric Authentication
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.25118v1 Announce Type: new Abstract: Biometric authentication systems increasingly use privacy-preserving mechanisms to protect sensitive templates. However, the authentication interface itself may still leak information that enables reconstruction attacks. Prior atta…

🅲 hạng C
26
LLM-Based Exogenous World Modeling for Dynamic Scheduling
📄 Paper arXiv cs.AI 25 ngày trước

arXiv:2610.29308v1 Announce Type: new Abstract: Dynamic scheduling requires dispatching online arrivals while anticipating future jobs, as poor decisions can compound downstream costs under nonlinear tardiness objectives. We show that a pretrained large language model (LLM) can …

🅲 hạng C
26
The Promise of Strategic Agentic Scambaiting
📄 Paper arXiv cs.CR 10 ngày trước

arXiv:2611.08170v1 Announce Type: new Abstract: Scammers have increasingly adopted AI-driven capabilities, evolving from automated message generation to fully agentic conversational systems that scale operations and maximize the exploitation of fraudulent resources before detect…

🅲 hạng C
26
Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction
📄 Paper HF Daily Papers 24 ngày trước

Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-to-end reconstruction of 3D assets and their scene layouts, but still struggle with fine-grained scene geometry and asset quality. Meanwhile, specialized 3D object…

🅲 hạng C
26
Data-Void Exploits in Web-Searching LLMs
📄 Paper arXiv cs.CR 24 ngày trước

Bài báo phát hiện một lỗ hổng mới gọi là data‑void exploit trong các LLM thực hiện web‑search. Khi nội dung đáng tin cậy thiếu hụt, kẻ xấu có thể đưa tin giả vào “kho dữ liệu trống” và LLM sẽ trích dẫn chúng trong câu trả lời, gây lan truyền thông tin sai lệch.

🅲 hạng C
26
Leaking Secrets from Air-Gap Computers by Spelling Radio Signals from RAM (2024)
📄 Paper Hacker News 15 ngày trước ▲ 204 · 💬 97 thảo luận

Nghiên cứu về kỹ thuật tấn công trích xuất dữ liệu mật từ máy tính cô lập (air-gapped) bằng cách phát tín hiệu vô tuyến từ thanh RAM. Đây là tài liệu nghiên cứu phần cứng và bảo mật phần cứng rất đáng chú ý.

🅲 hạng C
25
From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.23534v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computational footprint. These characteristics also make them candidates for future autonomous malware, where connectiv…

🅲 hạng C
25
Sign Here: Attributing a Source for a More Trustworthy Software Supply Chain
📄 Paper arXiv cs.CR 25 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
Automated Post-Exploitation Attack Chain Exploration Based on a Phase-guided Hybrid Planning-Monte Carlo Tree Search Algorithm
📄 Paper arXiv cs.CR 21 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
Denoising the US Census: Succinct Block Hierarchical Regression
📄 Paper arXiv cs.CR 5 giờ trước

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…

🅲 hạng C
25
Understanding Large Language Models as Numerical Optimizers
📄 Paper arXiv cs.AI 17 ngày trước

Nghiên cứu đánh giá năng lực và hạn chế của các mô hình ngôn ngữ lớn (LLM) khi đóng vai trò là trình tối ưu hóa số học (numerical optimizers) trong không gian có chiều cao. Paper cung cấp khung đánh giá phân tách chất lượng giải pháp và lỗi thực thi.

🅲 hạng C
24
Scaling Parameter-Efficient Fine-Tuning for Brain Encoding
📄 Paper HF Daily Papers 28 ngày trước

Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones. Using neural data to train large models from scratch or fully fine-tune them after task-pretraining has proven difficult because neural …

🅲 hạng C