cập nhật 56 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5337, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery
📄 Paper arXiv cs.CR 25 ngày trước

arXiv:2610.28802v1 Announce Type: new Abstract: How much does an agent harness affect vulnerability discovery, and does its value depend on the model? We study 24 model-runner configurations using an open-source harness on a production codebase whose vulnerabilities were non-pub…

🅲 hạng C
28
Do AI-for-Science Agents Preserve Model Safety?
📄 Paper arXiv cs.AI 21 ngày trước

arXiv:2610.32045v1 Announce Type: new Abstract: AI-for-Science agents are increasingly being used for formulating scientific hypotheses, running autonomous experiments, and interpreting evidence. These agents are constructed by integrating a large language model (LLM) into a dom…

🅲 hạng C
28
SEMPRE: Semantic-Aware Protocol Reverse Engineering via Consistency-Driven Joint Optimization
📄 Paper arXiv cs.CR 21 ngày trước

arXiv:2610.31844v1 Announce Type: new Abstract: Protocol reverse engineering (PRE) is essential for understanding undocumented or proprietary communication formats, enabling security-critical tasks such as vulnerability discovery, malware C2 analysis, and IDS signature generatio…

🅲 hạng C
28
Agentic AI Defense: Decode-Time Provenance Binding for MCP
📄 Paper arXiv cs.CR 21 ngày trước

arXiv:2610.31974v1 Announce Type: new Abstract: Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate cross-modal trust laundering, in which instructions concealed in an email-signatur…

🅲 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
LLM WikiLeaks: Uncovering URL-Based Capability Extension and Security Circumvention in Agentic Message Boards
📄 Paper arXiv cs.CR 20 ngày trước

arXiv:2610.34542v1 Announce Type: new Abstract: Autonomous agents have been observed acting beyond their assigned tasks, accessing unauthorized systems, and establishing communication channels to exchange information, yet the Web and network-level techniques they use to extend t…

🅲 hạng C
28
AgentOrch: How Close Can Global Orchestration Come to Step-by-Step Interaction?
📄 Paper arXiv cs.AI 20 ngày trước

arXiv:2610.33375v1 Announce Type: new Abstract: Enterprise workflow agents typically rely on step-by-step interaction (Step-by-Step): the agent executes an action, observes its result, and invokes a large language model (LLM) again to decide the next step. Global orchestration (…

🅲 hạng C
28
CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems
📄 Paper arXiv cs.AI 20 ngày trước

arXiv:2610.33539v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse tasks. Yet their memory and collaboration architectures often remain static, constraining continued adaptation and improv…

🅲 hạng C
28
Data Governance for Generative and Agentic AI : Technology, Law, Economics, and Security
📄 Paper arXiv cs.AI 20 ngày trước

arXiv:2610.33605v1 Announce Type: new Abstract: This book develops a unified governance framework for systems that retrieve, generate, infer, remember and act on information from large language models and retrieval augmented pipelines to autonomous multi agent systems. Eleven ch…

🅲 hạng C
28
OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning
📄 Paper arXiv cs.AI 19 ngày trước

arXiv:2610.36335v1 Announce Type: new Abstract: Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowl…

🅲 hạng C
28
Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol
📄 Paper arXiv cs.CR 19 ngày trước

arXiv:2610.36108v1 Announce Type: new Abstract: LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata used to describe those tools creates a prompt-injection surface. Within this established tool-poisoning surfa…

🅲 hạng C
28
PrivacyFlow: Privacy in AI Agents through Information Flow Analysis and Consequence-Aware Risk Management
📄 Paper arXiv cs.CR 14 ngày trước

arXiv:2610.40714v1 Announce Type: new Abstract: Autonomous LLM agents executing multi-step workflows over personal data often misalign with user privacy expectations and leak sensitive, out-of-context information. Although Contextual Integrity (CI) formalizes this problem, exist…

🅲 hạng C
28
Can Large Language Model Agents Learn by Watching Tutorial Videos?
📄 Paper HF Daily Papers 16 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
AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
📄 Paper arXiv cs.CR 13 ngày trước

arXiv:2611.00729v1 Announce Type: new Abstract: Language-model agents commonly collapse two decisions that security systems separate: selecting an action and determining whether that action is authorized. When a model exercises standing authority, indirect prompt injection can c…

🅲 hạng C
28
Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation
📄 Paper arXiv cs.CR 13 ngày trước

arXiv:2611.00923v1 Announce Type: new Abstract: The communication topology of Large Language Model Multi-Agent Systems (LLM-MASs) governs how information propagates among agents and encodes critical domain knowledge and expert workflow design. It is valuable intellectual propert…

🅲 hạng C
28
Performance, Scalability and Maintenance: An Experimental Study of RPA vs. Autonomous Agents in the Healthcare Domain
📄 Paper arXiv cs.AI 12 ngày trước

arXiv:2611.03853v1 Announce Type: new Abstract: Healthcare information systems are fragmented, and retrieving data from legacy web portals is a recurrent need. Robotic Process Automation (RPA) is deterministic but sensitive to interface changes, whereas autonomous agents based o…

🅲 hạng C
28
ProofPaths: An AI Agent Framework for Assessing Student Reasoning
📄 Paper arXiv cs.AI 12 ngày trước

arXiv:2611.03882v1 Announce Type: new Abstract: Students can use large language models to complete assignments, but a correct solution does not establish whether they understand the reasoning behind it. Individualized interviews can probe that understanding but require recurring…

🅲 hạng C
28
RuntimeTickets: Source-Grounded Security Obligations for Agent Skills
📄 Paper arXiv cs.CR 12 ngày trước

arXiv:2611.03772v1 Announce Type: new Abstract: Third-party Agent Skills extend what an autonomous agent can do, but a malicious Skill can hide data exposure or output manipulation inside a legitimate workflow. Neither reading a Skill's description nor granting it tool permissio…

🅲 hạng C