cập nhật 22 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5420, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

31
Agent-ZTA: A chain-Aware Zero Trust Model for Bidirectional Security-State Propagation and Runtime Containment in Multi-Agent Delegation
📄 Paper arXiv cs.CR 20 giờ trước

arXiv:2611.18999v1 Announce Type: new Abstract: Multi-agent systems increasingly delegate tasks and permissions across chains of autonomous agents that invoke protected tools. Although agent identities and delegated credentials may remain valid throughout a workflow, the securit…

🅲 hạng C
31
Compositional Exploits in Autonomous Coding Agents: Attack Mechanics and Ephemeral Defense
📄 Paper arXiv cs.CR 20 giờ trước

arXiv:2611.19764v1 Announce Type: new Abstract: Autonomous coding agents (such as Antigravity, Claude Code, Cursor, and OpenHands) rely on third-party tools to inspect files, run commands, and call external APIs. Today's security auditors evaluate these tools almost entirely in …

🅲 hạng C
30
Security of Deep Research Agents: Attack Surface, Defenses, Benchmarks, and Agenda Seeding against Research Planning
📄 Paper arXiv cs.CR 20 giờ trước

arXiv:2611.20045v1 Announce Type: new Abstract: Deep research and agentic search agents autonomously retrieve content from the open web and generate reports with citations, and their outputs are often taken directly as research conclusions. This paper systematizes security resea…

🅲 hạng C
27
Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns
📄 Paper arXiv cs.AI 20 giờ trước

arXiv:2611.19244v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers specialized capabilities to language-model agents, but its cross-domain effects on interaction remain unclear. We investigate how OPD reshapes ReAct interaction patterns across mathematics, AL…

🅲 hạng C
27
HalluProbe: Exploiting VLM Hallucinations for Backdoor Detection
📄 Paper arXiv cs.CR 20 giờ 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
26
Cognitive Multi-Agent Search and Rescue: Language-Grounded Hierarchical Reinforcement Learning for Collaborative Robotics
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.13161v1 Announce Type: new Abstract: Effective search and rescue (SAR) operations require autonomous systems capable of coordinating multiple heterogeneous agents, adapting to dynamic hazards, and aligning with human mission intent. Existing language-guided reinforcem…

🅲 hạng C
26
Securing Multi-Agent Systems by Design
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.17883v1 Announce Type: new Abstract: Multi-agent systems solve complex tasks by decomposing them into subtasks, delegating the subtasks to agents, and aggregating the agents' responses using an aggregation rule. Malicious agents can manipulate the final solution by pr…

🅲 hạng C
25
Where Autonomy Belongs: A Separation of Powers for Agentic Program Evolution
📄 Paper arXiv cs.AI 4 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 5 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
Open Challenges and Opportunities in Human-Agent Systems
📄 Paper arXiv cs.AI 4 ngày trước

Paper tổng hợp về 'Human-Agent Systems': những thách thức khi agentic AI thực thi task dài hạn thay mặt con người, nhấn mạnh tương tác human-agent, phối hợp năng lực và duy trì mối quan hệ trong môi trường socio-technical. Áp dụng khung AAMAS cho các hệ thống agent. Hữu ích nếu bạn xây agent cần phối hợp với người dùng.

🅲 hạng C
24
Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2510.10140v3 Announce Type: replace-cross Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of downstream applications, including tropical cyclone (TC) prediction. In thi…

🅲 hạng C
24
Seeing Is Not Believing: Counterfactual Lesion Erasure Teaches a Small Medical Vision-Language Agent to Report Only What the Image Shows
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.13006v1 Announce Type: new Abstract: Medical vision-language models (VLMs) often report a finding because the question names it; standard benchmarks miss this. From public segmentation datasets we build counterfactual views without manual annotation: the lesion erased…

🅲 hạng C
23
A Bleichenbacher bit-by-bit oracle attack from partial message knowledge
📄 Paper arXiv cs.CR 20 giờ trước

arXiv:2611.20277v1 Announce Type: new Abstract: Oracle attacks show the importance of a correct implementation of cryptographic standards when translated into code. A notable example is the Bleichenbacher attack on RSA with PKCS#1 v1.5 padding and all the improvements that have …

🅲 hạng C
23
A physics-constrained deep reinforcement learning method for autonomous mission planning of Titan deep space probes
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.15389v1 Announce Type: new Abstract: Titan is a compelling target for future deep space exploration, while its extreme Earth-Titan distance and complex environment make continuous ground-in-the-loop planning impractical. Existing planning methods, primarily developed …

🅲 hạng C
23
Look Here, Then Decide: Small Decision Models in a Harness Find Memory-Safety Vulnerabilities at Scale on Commodity GPUs
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.16565v1 Announce Type: new Abstract: We ask whether small, open-weight decision models can support vulnerability discovery in open-source software at scale and what the surrounding system must provide. These models answer a typed question in one forward pass, returnin…

🅲 hạng C
23
Model-Based Authoring of SOC Simulation Exercises for Cybersecurity Education
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.14227v1 Announce Type: new Abstract: Cybersecurity training and classroom exercises with a virtual Security Operations Center (SOC) combine alerts, evidence, timeline entries, learner tasks, and assessment items that must remain consistent across an evolving incident.…

🅲 hạng C
22
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…

🅲 hạng C
22
Advancing Quantization for R&R Models with Microscaling Formats
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17501v1 Announce Type: new Abstract: Recommendation and Ranking (R&R) models, particularly in digital advertising, require massive inference throughput but exhibit extreme sensitivity to precision loss. Unlike Large Language Models (LLMs) that frequently tolerate quan…

🅲 hạng C
22
On the Same Track: Privacy Leaks in Electric Rail Transport via Magnetic Fields
📄 Paper arXiv cs.CR 1 ngày trước

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…

🅲 hạng C
21
PaperCritic: Training AI Reviewers to Assess the Soundness of Papers
📄 Paper HF Daily Papers 5 ngày trước

As AI conference submissions grow rapidly, AI reviewers are being considered as an alternative. However, simply imitating human reviewing is problematic because reviewing serves multiple purposes, including evaluating papers' soundness, interestingness, and clarity, the last two …

🅲 hạng C