cập nhật 45 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.3 giờ sau khi CVE được công bố (n = 5278, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
Compositional Exploits in Autonomous Coding Agents: Attack Mechanics and Ephemeral Defense
📄 Paper arXiv cs.CR 5 ngày 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
27
Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent
📄 Paper arXiv cs.CR 3 ngày trước

Bài nghiên cứu mới giới thiệu mô hình Envelope Layer cho LLM Agent, đánh giá trọng lượng các thành phần và cách giải quyết rủi ro khi công cụ MCP và bộ nhớ lâu dài đồng thời tồn tại. Điều này giúp cải thiện an toàn và giảm rủi ro lây nhiễm nội dung độc hại trong AI Agent.

🅲 hạng C
26
Condensing Law of Security Information
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.17918v1 Announce Type: new Abstract: Scaling laws indicate that the generalization error of a large language model (LLM) decreases monotonically with model size once data is sufficient, and the corollary that larger models outperform smaller ones is now widely accepte…

🅲 hạng C
👁 Trúng danh sách theo dõi: kw:zero-day
25
Toward a Science of AI Agent Societies
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.25404v1 Announce Type: new Abstract: AI agents are rapidly evolving from isolated personal assistants into networked actors that interact with one another at scale. We envision the emergence of AI agent societies, with their own social and economic dynamics, as a new …

🅲 hạng C
25
Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.19237v1 Announce Type: new Abstract: Human approval provides effective control only if rejected work stops and authorized work completes. We formalize refusal safety and bounded authorization completeness, and audit three execution boundaries: the model selects a call…

🅲 hạng C
24
Securing Multi-Agent Systems by Design
📄 Paper arXiv cs.CR 6 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
23
A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights
📄 Paper HF Daily Papers 3 ngày trước

Pretrained language models (LMs) remain unreliable on exact multi-digit arithmetic without gradient fine-tuning or external tool interpreters. We introduce closed-form, zero-gradient circuit-grafting primitives that compile deterministic computation directly into pretrained LM we…

🅲 hạng C
23
LLMs are Vulnerable to Malicious Requests with Indistinguishable Intent
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.17818v1 Announce Type: new Abstract: Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and obse…

🅲 hạng C
23
Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment
📄 Paper HF Daily Papers 6 ngày trước

Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models. The causes of abstention fall into three perspectives: ambiguity in the Query (Q), limits of Model Knowledge (MK), and misalignment wi…

🅲 hạng C
22
Causal Overtaking in Fair Transaction Ordering
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.26100v1 Announce Type: new Abstract: Fair transaction ordering protocols aim to mitigate front-running using replica-local arrival orders, but prior work often assumes a single submission origin for each responsive transaction. We identify causal overtaking, in which …

🅲 hạng C
21
Image Watermarking With Memory Across Reissuance
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.23363v1 Announce Type: new Abstract: Publishers often revise and reissue images, yet valid watermarks may persist on superseded releases or unapproved edits. Even a current release can contain regions last authorized at different revisions. We introduce and formalize …

🅲 hạng C
21
Data Poisoning Attacks to Locally Differentially Private Triangle Counting Protocols
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.23701v1 Announce Type: new Abstract: Local differential privacy (LDP) has become a crucial paradigm for privacy-preserving graph analytics, enabling graph analytics tasks such as subgraph counting without requiring a trusted curator. However, while LDP provides strong…

🅲 hạng C
21
Fidelity Regret: Measuring Simulator Misspecification in Verifiable Design
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.22263v1 Announce Type: new Abstract: RLVF assumes the verifier evaluates the quantity of interest. In genetic-circuit design, a topological verifier can establish that a program is a valid circuit computing the target function, whereas ranking its physical performance…

🅲 hạng C
21
Bajillion: Cryptographic Clearing for Micropayments
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.21883v1 Announce Type: new Abstract: Much of the web is funded by advertising, a model that erodes as humans delegate browsing to AI agents acting on their behalf. A natural replacement is for agents to pay for what they consume, often a fraction of a cent per request…

🅲 hạng C
21
CaFe: Causally Faithful Conditional Traffic Scenario Generation
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.22855v1 Announce Type: new Abstract: Language-conditioned traffic simulation enables scalable test scenarios steered by natural language. The goal is to control selected agents while surrounding traffic reacts to their observed behaviour. For example, a vehicle instru…

🅲 hạng C
21
Can Verifiable PIR Match the Online Efficiency of SimplePIR?
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.22911v1 Announce Type: new Abstract: Verifiable Private Information Retrieval (vPIR) ensures that a malicious server cannot return tampered database records, but it traditionally incurs significant overhead compared to classical PIR.Recent advancements, notably VeriSi…

🅲 hạng C
20
DrawScore: Evaluating Generated CAD Models against Engineering Drawings
📄 Paper HF Daily Papers 4 ngày trước

Automatic CAD generation is commonly evaluated with volumetric IoU, Chamfer Distance, and surface F-score, which barely penalize local errors that occupy only a small fraction of a part's volume or surface area, such as a misplaced hole or a slot on the wrong face, even though su…

🅲 hạng C
20
When the Spec Sheet Lies: Injection Attacks on LLM-Generated Compliance Artifacts
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.19090v1 Announce Type: new Abstract: As Large Language Models (LLMs) become used more commonly across a variety of fields, a growing body of research has highlighted particular concerns surrounding model security. Notably, prompt injection attacks, where malicious ins…

🅲 hạng C
20
Security Authentication as Protective Friction: Understanding the Dual Effects of Authentication Measures in e-Government Platform
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.19435v1 Announce Type: new Abstract: E-Government platforms, such as government credit platforms, handle highly sensitive personal data, requiring stringent security authentication (e.g., facial recognition, multi-factor verification) that protects users but impedes t…

🅲 hạng C
20
Advancing Quantization for R&R Models with Microscaling Formats
📄 Paper arXiv cs.AI 6 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
20
Online Allocation with Differential Privacy
📄 Paper arXiv cs.CR 6 ngày trước

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…

🅲 hạng C
20
AuXSpec: Learning to Autoformalize Program Specifications via Executable Postconditions
📄 Paper HF Daily Papers 6 ngày trước

Formal specifications define intended program behavior and underpin verification, but writing them in theorem provers such as Lean is slow and expertise-intensive, making specification a major bottleneck to scaling formally correct code. Autoformalization from natural-language pr…

🅲 hạng C