Published file metadata, source observations, indicators, and research history in one bounded catalog.
99Reachable catalog records
1 / 5Current catalog page
24Maximum records per page
0Samples downloaded by this page
Feed collection status
Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.
src_fb50be84b835134c75Collection status unverifiedLast successful batch: Unverified
Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.
99 MATCHING RECORDSMETADATA ONLY / SOURCE ATTRIBUTION PRESERVED
arXiv:2609.15039v3 Announce Type: replace Abstract: User prompts provided to large language models (LLMs) may contain private information. One way to protect them is to execute the LLM inside a trusted execution environment (TEE). However, this results in slow inference times as current TEEs are significantly slower than GPUs for LLM inference. To circumvent this, Tram\`er and Boneh (2019) propose
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07931v1 Announce Type: new Abstract: Rewriting a hot path from Python into Rust is a common way to speed up security analytics, and large speedups are routinely reported. A rewrite usually changes the language and the algorithm at once, so a single factor can credit the language with a gain that comes from a better algorithm. We study this on a sliding window threat scorer modelled on t
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07334v1 Announce Type: cross Abstract: Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring known inputs to find hidden capabilities such as backdoors. We propose Weight Oracles, fine-tuned language models that diagnose properties of a target network by reading its raw weights directly, witho
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2609.14098v2 Announce Type: replace Abstract: Large language models are increasingly used in blockchain forensic investigations to interpret unverified smart contract bytecode. Their robustness has not been systematically tested against contracts adversarially designed to mislead analysis. We evaluate 22 frontier models on 13 purpose-built contracts (9 deception vectors, 4 controls) across s
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08678v1 Announce Type: new Abstract: Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to as the \emph{draft model}, to generate candidate tokens and then verifying them with the target model for acceptance or rejection. Prior studies primarily focused on the efficiency-utility tr
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07723v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activation depends on explicit trigger patterns in the user input, so modern guardrails are built to sanitize the input space. We challenge this assumption with a novel answer-side backdoor for multi-turn dialo
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08410v1 Announce Type: cross Abstract: A recognizer that compares rotation-invariant descriptors sees a surface only up to the fiber of the descriptor. We measure this fiber by its radius in the orbit distance from the enrolled surface. A large radius admits decoys, that is, distant shapes that pass the matcher. A small radius discloses the enrolled shape to anyone who captures the stor
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07282v1 Announce Type: new Abstract: Protecting critical infrastructure increasingly depends on continuously verifying large IoT fleets against formal security specifications at runtime. Yet the runtime-verification (RV) pipelines proposed for this task are typically single-host prototypes whose monitors read a shared log file, with no resilience to the failures such deployments incur:
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07005v1 Announce Type: cross Abstract: We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio. The protocol masks frequency components of the perturbation in the short-time Fourier transform (STFT) domain and measures attack success and audio-span representations. On 520 AdvBench prompts, the primary judge labels 76.7% of adversarial input
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07345v1 Announce Type: new Abstract: IAM policy analysis typically emphasizes the authorization capabilities encoded in a policy, but security analyst review priority may also depend on the behavioral and environmental context surrounding a policy event. This paper evaluates whether contextual information provides measurable incremental value for interpretable IAM policy risk prioritiza
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08255v1 Announce Type: new Abstract: Many organizations adapt large pretrained models to their own tasks by fine-tuning on private data. Several of these parties often hold data for the same task and wish to fine-tune a model together without pooling that data. Federated learning (FL) enables joint fine-tuning, but reconstruction attacks on shared intermediate values (the model or its g
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07256v1 Announce Type: new Abstract: AI agents powered by large language models (LLMs) can perform complex tasks but may harm the systems they operate in, either intentionally or unintentionally. Existing agent monitoring approaches rely on rule-based guardrails or LLM-based trace auditing. However, rule-based guardrails can be bypassed through obfuscation and may miss harmful actions b
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07776v1 Announce Type: new Abstract: Website fingerprinting infers the websites visited by users from encrypted traffic metadata. However, models trained under fixed collection conditions often degrade as website sets, collection times, network paths, browsers, or defenses change. Existing transferable attacks either rely on handcrafted perturbations of individual traces or adapt langua
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07532v1 Announce Type: new Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks including defenses at decoding stage that leverage models' hidden states. However, existing decoding-stage defenses suffer from two limitations. First, they introduce a trade-off between safety and over-ref
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07310v1 Announce Type: new Abstract: Security operations centres and national incident-response teams defending critical infrastructure collect abundant threat data yet struggle to turn it into actionable intelligence. A malware sandbox produces detailed behavioural evidence, but as a large, unranked report whose confidence is unstated. We present CG-CTI, an operational pipeline that co
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07089v1 Announce Type: new Abstract: LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluations treat these threats separately and ask whether a traj
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07759v1 Announce Type: cross Abstract: Byzantine quorum safety relies on correct replicas refusing to sign conflicting values. A replica that loses its protocol state during recovery but retains its identity and signing key may forget an earlier vote. We study certificates formed by matching signed votes from at least $q$ of $n$ replicas, assuming that each correct replica avoids confli
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07854v1 Announce Type: new Abstract: Ransomware continues to encrypt files during the interval between attack onset and detection. Real-time backups can mitigate this damage by preserving files before they are modified. The previously proposed Real-Time Open-File Backup System (ROFBS) triggers backups primarily on file-open events. However, the file lifecycle offers several candidate tr
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08417v1 Announce Type: cross Abstract: Recent advances in LipSync generation technology have led to the creation of highly realistic videos, posing severe societal risks. However, existing defense strategies struggle against LipSync forgeries, as advanced LipSync generation methods not only achieve better lip synchronization but also eliminate visual artifacts. An important reason is th
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07009v1 Announce Type: new Abstract: Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313-prompt StrongREJECT slice, using five multimodal models and an additional appendix evaluation of InternVL3.5-8B. The harmful instruction is held constant across conditions
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07635v1 Announce Type: new Abstract: Compiler-introduced security bugs (CISBs) arise when an optimization, lowering, or instrumentation decision changes a security-relevant property of the generated program. They are difficult to study because their evidence is distributed across issue reports, reduced tests, historical configurations, and compiler artifacts; a security-related report a
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08460v1 Announce Type: cross Abstract: We propose a simple framework for constructing differentially private confidence regions \textit{in one shot}, i.e., by adding noise only to the final resampling quantile instead of privatizing the estimator computed on each resample. The cost of privacy of our procedure is only logarithmic in the number of resamples $B$ under with-replacement ($m$
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2506.01325v3 Announce Type: replace Abstract: Single sign-on (SSO) enables a user to log into multiple websites, called relying parties (RPs), by her username and credential set up in another trusted web system, called the identity provider (IdP). Identity transformations are proposed in UppreSSO to provide privacy-preserving SSO services, preventing both IdP-based login tracing and RP-based
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
A filename, label, or report mention alone does not establish maliciousness. Observation dates describe cited sources; collection dates describe this local metadata catalog. No malware samples are stored, fetched, or executed by these pages.