cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5178, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
OmniMechanism Design for Human-AI Collaboration with Impressionable Minds
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00441v1 Announce Type: new Abstract: As AI systems are increasingly deployed in high-stakes domains such as healthcare, effectively integrating human expertise with AI outputs is critical for reliable decision-making. A substantial body of theoretical work studies opt…

🅲 hạng C
20
Few Trials, Many Metrics: Beta Mixtures for Low-Budget AI Evaluation
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00474v1 Announce Type: new Abstract: Evaluating a stochastic AI system often requires many repeated samples per instance, especially for metrics defined over long horizons. Recent work has shown that modeling instance-level success probabilities with a Beta distributi…

🅲 hạng C
20
State-Aware Activation Recomputation with Replay Contracts and Selective Preservation
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00590v1 Announce Type: new Abstract: Activation recomputation saves accelerator memory by replaying forward segments during the backward pass, but replay is only correct if it sees the state the original forward pass saw. Mutable buffers, aliased bytes and random-gene…

🅲 hạng C
20
X-World 1.6: Building Controllable Virtual Cities with World Models
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00596v1 Announce Type: new Abstract: Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report pres…

🅲 hạng C
20
Editing the Goal: Per-Token SAE Steering and Its Depth Limits in $\pi_{0.5}$
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00602v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have recovered interpretable, causally relevant features in robot foundation models (RFMs) such as $\pi_{0.5}$ (arXiv:2603.19183, arXiv:2603.19233). SAE features on individual instruction tokens are less …

🅲 hạng C
20
Practical Preimages for 19- and 20-Step SHA-256 with Standard Padding
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.00512v1 Announce Type: new Abstract: We present practical preimage attacks on 19- and 20-step SHA-256 that respect the standard IV, Davies-Meyer feed-forward, and full FIPS 180-4 padding, for arbitrary prescribed 256-bit targets. Building on Basra's algebraic selector…

🅲 hạng C
20
Cross-Evidence Authorization State Learning for Runtime Detection of Broken Object-Level Authorization in Black-Box Web Applications
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.00738v1 Announce Type: new Abstract: Broken object-level authorization (BOLA) remains difficult to detect in black-box Web applications because external runtime monitors generally lack access to source code, authorization policies, and object-ownership records. This p…

🅲 hạng C
20
Intent-Bound Authorization for Cryptocurrency Withdrawals Under Backend Compromise
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.00839v1 Announce Type: new Abstract: Binance's preliminary account of its October 2026 attack raises a custody question that key protection alone cannot answer: how can a provider prevent unauthorized withdrawals when an attacker controls a service permitted to reques…

🅲 hạng C
20
VeilFL: Two-Stage Accountability for Anonymous Federated Learning
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.01082v1 Announce Type: new Abstract: Anonymous credentials can hide which registered client participates in federated learning, but their unlinkability also makes repeated misconduct difficult to associate. We present VeilFL, a two-aggregator protocol that adds staged…

🅲 hạng C
20
Detecting Generated-Depth Injection Attacks on RGB-D Place Authentication
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.01550v1 Announce Type: new Abstract: Advances in monocular depth estimation (MDE) now let an attacker generate depth from publicly available RGB images and submit forged RGB-D queries. Such attacks break a core assumption of RGB-D place authentication: that depth come…

🅲 hạng C
20
Attack Patterns in Cross-chain Bridges: A Trust-based Empirical Analysis
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.01587v1 Announce Type: new Abstract: The rapid growth of multiple blockchain ecosystems has made cross-chain bridges essential for transferring assets and information across independent blockchains. Their multi-component architectures, cross-chain trust assumptions, a…

🅲 hạng C
20
CertClaim: Towards Certified Model-Claim Verification for Coding-Agent Services
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.01950v1 Announce Type: new Abstract: Coding-agent services are priced by the model they claim, making the verification of such model claims crucial for their users. In this paper, we reveal that existing model auditing methods rely on a latent assumption that the depl…

🅲 hạng C
20
Accelerating QUIC Encryption in WebAssembly Using WASM-SIMD
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.01989v1 Announce Type: new Abstract: WebAssembly (Wasm) runs untrusted code in a portable, lightweight sandbox and is increasingly used to host services on shared servers and edge platforms. Running the QUIC transport protocol inside Wasm would let each application ch…

🅲 hạng C
20
One String to Rule Them All: Measuring Consent Under the IAB Global Privacy Platform
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.02014v1 Announce Type: new Abstract: Many privacy regulations, including the California Consumer Privacy Act (CCPA), require websites to honor users' opt-out choices. To facilitate this process, industry has introduced technical standards such as the IAB Global Privac…

🅲 hạng C
20
Query-efficient scan-and-search watermark localization
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.02030v1 Announce Type: new Abstract: Recently, the detection of AI-generated content has been of particular importance in various fields of our society. For accountability purposes, many large language models (LLMs) have implicitly watermarked their outputs. Localizin…

🅲 hạng C
20
ZT-DAC: ML-Driven Dynamic Access Control Policy for Zero Trust in DER Networks
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.02107v1 Announce Type: new Abstract: The increasing penetration of Distributed Energy Resources (DERs) in the smart grid has significantly expanded the cyber-attack surface. Traditionally, DER networks rely on static role-based access control (RBAC) mechanisms that as…

🅲 hạng C
20
Alignment Faking Depends on the Value, Not Just the Model
📄 Paper arXiv cs.AI 15 ngày trước

arXiv:2611.03650v1 Announce Type: new Abstract: Language models can follow a directive when they believe they are monitored and abandon it when they believe they are not, a pattern termed Alignment Faking. Prior work establishes this for harmful-content objectives and a handful …

🅲 hạng C
20
Functional-Group Knowledge Is Structured in Language Models Before It Is Spoken
📄 Paper arXiv cs.AI 15 ngày trước

arXiv:2611.03684v1 Announce Type: new Abstract: Language models serve as the reasoning core of agents for chemistry and materials science, where they must interpret molecular structure before planning syntheses or proposing materials. Yet their outputs show only what they say, n…

🅲 hạng C