Published file metadata, source observations, indicators, and research history in one bounded catalog.
99Reachable catalog records
2 / 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:2610.07645v1 Announce Type: new Abstract: Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by injecting malicious triggers, behaviors, or false facts into individual experiences or extracted skills. However, such attacks are easily detected, and the injected malicious behaviors
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08061v1 Announce Type: new Abstract: Supervised fine-tuning can substantially improve the downstream utility of large language models (LLMs) but may compromise their safety. Existing safety-preserving methods constrain downstream updates using safety-related parameters or subspaces, but mainly focus on safety preservation rather than joint safety and utility enhancement, lack a theoreti
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2501.18158v4 Announce Type: replace Abstract: Cryptocurrencies are widely used, yet current methods for analyzing transactions often rely on opaque, black-box models. While these models may achieve high performance, their outputs are usually difficult to interpret and adapt, making it challenging to capture nuanced behavioral patterns. Large language models (LLMs) have the potential to addre
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08405v1 Announce Type: cross Abstract: Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. Existing research primarily compares prompting strategies using aggregate performance metrics, providing limited insight into why models fail or how prompts can be improved systematically. We propose F
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2609.04820v2 Announce Type: replace Abstract: Sandbox execution and memory forensics are among the most constrained resources in malware triage. Static analysis can scale to millions of files, whereas dynamic and memory analysis require minutes of analyst controlled infrastructure for each sample. Despite this difference, multimodal ransomware detectors often apply every modality to every sa
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2608.26423v2 Announce Type: replace-cross Abstract: This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier's confident decisions can be trusted. This framework, the Latent Diagnostic Taxonomy, consists of (i) constructing a dimensionality-optimized classifier, in which the embed
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07677v1 Announce Type: cross Abstract: In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy leakage. State-of-the-art privacy defenses, standard training techniques such as MixUp and Adversarial Training, and undefended models all leak training images at rates 1.16 to 6.59 times higher on Fac
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07873v1 Announce Type: new Abstract: The EU Cyber Resilience Act (CRA), Regulation (EU) 2024/2847, makes product cybersecurity a lifecycle obligation for products with digital elements on the EU market: risk assessment, vulnerability handling, conformity documentation, and Article 14 incident- and vulnerability-reporting readiness must be operational before market placement. Small and m
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07510v1 Announce Type: new Abstract: Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies a model with a backdoor: hidden behavior that produces malicious outputs when a particular input pattern appears. Focusing on software-engineering agents, we ask whether such backdoors survive the d
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07519v1 Announce Type: cross Abstract: Automatic sign language translation (SLT) has entered consumer products, turning American Sign Language into English text for dictation, messaging, and queries put to a conversational assistant. Child-facing AI and platform trust-and-safety tooling decide on text, using filters on minor accounts and grooming classifiers that score chat messages. A
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07212v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) trains a language model on problems that may themselves be confidential, and the trained model can reveal which problems it saw. We study RLVR under prompt-level differential privacy: the released weights must be ({\epsilon},{\delta})-differentially private with respect to the presence of any on
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2605.30732v2 Announce Type: replace-cross Abstract: While quantum position verification aims to certify a prover's location using quantum information, existing security definitions only guarantee that part of the successful adversarial party is in the claimed location.This leaves open the possibility that a distributed team of adversaries can jointly simulate a prover in a way that defeats t
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07386v1 Announce Type: new Abstract: Network traffic analysis is central to network security, spanning tasks from intrusion detection to encrypted traffic classification. Existing approaches either train task-specific models that generalize poorly or rely on costly traffic foundation models that still struggle under distribution shift. We present NetAgent, the first agentic framework fo
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.06885v1 Announce Type: cross Abstract: Moving target defense (MTD) against advanced persistent threats (APTs) in industrial control systems (ICS) has well-established game-theoretic formulations, but their practical value hinges on equilibrium computation: full-rank value iteration is prohibitively expensive at industrial state dimensions, and the resulting defense strategies admit no c
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08771v1 Announce Type: new Abstract: An autonomous system that asks for a privileged physical action is usually gated on integrity evidence: a platform proves what it is running, and the request is granted or refused on that basis. Such a gate is normally treated as a predicate, yet the evidence behind it has an age, the decision that consumes it has a latency, and the physical system t
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.08066v1 Announce Type: new Abstract: Intrusion Detection Systems (IDS) struggle with imbalanced datasets like NSL-KDD, especially in detecting rare R2L and U2R attacks. This work describes a systematically optimized and explainable framework using a CNN-Transformer architecture to improve performance on highly imbalanced data. We decided to use XGBoost for feature selection and Focal Lo
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07489v1 Announce Type: new Abstract: Increasing connectivity to the outside world and the lack of inbuilt security mechanisms have made legacy intra-vehicular networks vulnerable to cyberattacks. Initial research focused on maximising detection accuracy for known and unknown attacks, often using large, full-precision machine learning models. However, embedding IDSs into vehicular electr
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07870v1 Announce Type: new Abstract: Bluetooth Low Energy (BLE) pairing establishes the cryptographic foundation for secure device communication. However, mainstream man-in-the-middle (MITM)-resistant pairing methods, such as Numeric Comparison and Passkey Entry, require user interfaces that implantable medical devices (IMDs) inherently lack, making Near-Field Communication (NFC)-assist
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.07518v1 Announce Type: cross Abstract: Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of available evaluations. This work asks a different question: Do the target behaviors optimized during supervised fine-tuning (SFT) leave readable evidence directly in checkpoint updates? We find that ha
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2609.30614v2 Announce Type: replace Abstract: Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM agents that compose tool calls. Work on agents that generate governance artifacts evaluates output quality, not who may authorize an artifact for use. A published policy is what the decision point e
First reported Oct 07, 2026 04:00 UTCCatalog metadata updated Oct 08, 2026 03:43 UTCOpen evidence record
arXiv:2610.06994v1 Announce Type: new Abstract: Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate removal from what the defense does to any model, and inherits the victim's start, which for three of BackdoorBench's sixteen attacks is a configuration file: WaNet, BPP and Input-Aware ship a MultiStep
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.