arXiv:2611.00414v1 Announce Type: new Abstract: We study the local differential geometry of a Fourier-based modular-addition circuit in a one-layer transformer whose algorithm has previously been reverse-engineered. For each of the five key Fourier frequencies, we restrict the m…
⏱ 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.
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…
arXiv:2611.00464v1 Announce Type: new Abstract: Deploying small language models on resource-constrained hardware requires compression, yet practitioners lack systematic guidance on how quantization, pruning, and post-compression recovery interact when combined. We present a fact…
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…
arXiv:2611.00496v1 Announce Type: new Abstract: System One decision models replace text generation with typed, probability-scored answers and are entering production. Answers execute without a person in the loop, and no multi-model audit exists on established bias benchmarks. We…
arXiv:2611.00550v1 Announce Type: new Abstract: Human sleep is organized into a small number of cycles per night: deep sleep dominates early cycles, REM lengthens toward morning, and light sleep clusters at cycle boundaries. These regularities have long been described qualitativ…
arXiv:2611.00580v1 Announce Type: new Abstract: Scientific discovery advances when evidence from different investigations is brought into contact. Yet paper-centric communication leaves experimental results fragmented, delayed, or unreported, creating a "scientific memory wall" …
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…
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…
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 …
arXiv:2611.00367v1 Announce Type: new Abstract: Defense systems for maritime assets must distinguish approaching benign craft from uncrewed surface vessels (USVs) with sufficient warning to act. Shore cameras using computer vision can separate hostile vessels from benign traffic…
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…
arXiv:2611.00587v1 Announce Type: new Abstract: Economic-state manipulation has emerged as a significant security threat to decentralized finance (DeFi), causing substantial financial losses. Existing studies predominantly characterize these attacks as price manipulation, focusi…
arXiv:2611.00594v1 Announce Type: new Abstract: Existing studies of vulnerable pre-installed Android apps identify dangerous behavior by checking whether an app invokes an API from a predefined set of security-sensitive APIs. These sets usually exclude generic APIs to avoid fals…
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…
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…
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…
arXiv:2611.01095v1 Announce Type: new Abstract: Many Automated Speaker Verification Systems (ASVs) commonly employ liveliness detection techniques, such as VoicePop, which identify genuine speech by analyzing low- frequency pop bursts from plosive phonemes using Gammatone Freque…
arXiv:2611.01127v1 Announce Type: new Abstract: The security guidance that bears on code is real but scattered. It lives across secure-development frameworks, verification standards, controls catalogues, threat taxonomies, and, increasingly, normative regimes such as the EU's NI…
arXiv:2611.01144v1 Announce Type: new Abstract: Despite their theoretical quantum attack resistance, practical implementations of post-quantum cryptography (PQC) algorithms remain susceptible to side-channel attacks. This includes all standard algorithms selected the National In…
arXiv:2611.01211v1 Announce Type: new Abstract: We present the first large-scale privacy and accessibility evaluation of cookie notices across 2,061 domains for blind and low vision (BLV) users. Using a Playwright-based crawler, a custom NVDA screen reader add-on, and the Lighth…
arXiv:2611.01218v1 Announce Type: new Abstract: Gaussian differential privacy (GDP) and zero-concentrated differential privacy (zCDP) are two competing privacy accounting frameworks, but they share similar minimax lower bounds in various estimation problems. Moreover, it is know…
arXiv:2611.01225v1 Announce Type: new Abstract: Machine-learning triage for memory forensics is usually validated on corpora whose benign class is asserted by provenance and never verified. We report a validation study of a graph-based triage pipeline for Windows memory images: …
arXiv:2611.01337v1 Announce Type: new Abstract: Sendrier's Support Splitting Algorithm (SSA) is the standard solver for the Permutation Equivalence Problem (PEP); its cost is dominated by a term that grows exponentially in the hull dimension. We study, mathematically, how much t…
arXiv:2611.01342v1 Announce Type: new Abstract: Prefill jailbreaks can cause safety-aligned language models to continue an unsafe assistant prefix even when they would refuse the same request under normal decoding. We study how the model's internal harmfulness and refusal signal…
arXiv:2611.01450v1 Announce Type: new Abstract: Cryptographically secure inference faces two practical challenges: making secure programming accessible to AI developers and data scientists, and achieving efficient execution across deployment environments. Developers must compose…
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…
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…
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…
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…
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…
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…
arXiv:2611.02042v1 Announce Type: new Abstract: Quantized neural networks store weights in dense memory, where bit flips caused by voltage scaling, aging, radiation, or deliberate attacks such as RowHammer can severely degrade model behavior. A single corrupted high-order bit ca…
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…
arXiv:2611.02123v1 Announce Type: new Abstract: We examine bounded retained history through a frozen predictive pilot and a subsequent allocation study on a curated UNSW-NB15 flow mirror. Both use an artificial release-order replay based on raw ltime ticks, with equal-tick recor…
arXiv:2611.02166v1 Announce Type: new Abstract: Machine learning models have shown exceptional accuracy for ballot classification in election systems. Recent research has demonstrated that these ballot classification models are vulnerable to adversarial example attacks. This is …
Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In gated linear recurrences, memory retention depends on state decay, which is shaped jointly by gate parameters A_log and dt_bias and by input activations. In con…
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 …
arXiv:2611.03651v1 Announce Type: new Abstract: Geometric certificates make mathematical claims about specified estimator objects, while robotic action requires a physical transform, a service decision, and timely proof support. We present CARD, a proof-carrying interface that k…
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…