Latest news

Advertisement
  1. AI Security via arXiv cs.CR

    Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming

    arXiv:2610.20941v1 Announce Type: new Abstract: We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors. An…

  2. Vulnerabilities via arXiv cs.CR

    Does Client Diversity Protect the Lightning Network? Evidence from the 2026 Core Lightning Shutdown

    arXiv:2610.20952v1 Announce Type: new Abstract: Client diversity is often cited as the Lightning Network's defence against a bug in any one implementation, yet LND runs…

  3. AI Security via arXiv cs.CR

    PAGE404: Breaking GPU Isolation Through Hardware-assisted Page Migration

    arXiv:2610.20962v1 Announce Type: new Abstract: NVIDIA's Grace Hopper (GH200) superchip represents a new generation of heterogeneous computing, tightly integrating a…

  4. Threat Intel via arXiv cs.CR

    Blind Watermarking of Software Repositories via Module Placement

    arXiv:2610.21031v1 Announce Type: new Abstract: Source-code watermarking supports provenance tracking by embedding a recoverable identifier in a software artifact. Many…

  5. AI Security via arXiv cs.CR

    Can Autonomous Vehicles Keep Their Cool? A Survey of Thermal Side-Channel and Perception Attacks

    arXiv:2610.21034v1 Announce Type: new Abstract: Autonomous vehicles (AVs) couple safety-critical perception to thermally constrained compute. Interfaces built for night…

  6. AI Security via arXiv cs.CR

    NOMAI: Scalable Federated Learning with Private Weights

    arXiv:2610.21059v1 Announce Type: new Abstract: The twin goals of privacy-preserving federated learning (FL) -- harnessing distributed data while protecting the parties…

  7. AI Security via arXiv cs.CR

    Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization

    arXiv:2610.21063v1 Announce Type: new Abstract: AI agents now pause for approval before they send money, delete files or email outsiders, and that approval is usually…

  8. Threat Intel via arXiv cs.CR

    Reaction Attack on CKKS Deployments with Asymptotically Optimal Query Complexity

    arXiv:2610.21127v1 Announce Type: new Abstract: We study a protocol-level reaction leakage in CKKS deployments where public coefficient-to-slot (C2S) evaluation keys are…

  9. Advertisement
  10. AI Security via arXiv cs.CR

    Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation

    arXiv:2610.21135v1 Announce Type: new Abstract: LLM-agent evaluation reports behavioral scores but leaves the identity of the deployed runtime stack unreported. A…

  11. AI Security via arXiv cs.CR

    ExecWeave: Cross-Layer Execution Provenance for Observable Agentic Software

    arXiv:2610.21146v1 Announce Type: new Abstract: Agentic software invokes tools, launches processes, accesses files, and communicates with local or remote services…

  12. AI Security via arXiv cs.CR

    CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data

    arXiv:2610.21151v1 Announce Type: new Abstract: Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured…

  13. AI Security via arXiv cs.CR

    FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence

    arXiv:2610.21194v1 Announce Type: new Abstract: Existing federated data condensation methods face privacy risks, as uploaded synthetic data may preserve sensitive…

  14. Threat Intel via arXiv cs.CR

    Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse

    arXiv:2610.21208v1 Announce Type: new Abstract: Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify…

  15. Vulnerabilities via oss-security

    CVE-2026-108764: Apache Kylin: job-driver UI proxy SSRF

    Posted by Li Yang on Oct 15 Severity: moderate Affected versions: - Apache Kylin 4.0.0 through 5.0.4 Description: Server-Side request forgery (SSRF) vulnerability in…

  16. Breaches via oss-security

    CVE-2026-108762: Apache Kylin: delete metadata backup path-confinement bypass

    Posted by Li Yang on Oct 15 Severity: moderate Affected versions: - Apache Kylin 4.0.0 through 5.0.4 Description: Path-confinement bypass during metadata backup deletion…

  17. Vulnerabilities via oss-security

    CVE-2026-108743: Apache Kylin: spark job OS command injection

    Posted by Li Yang on Oct 15 Severity: moderate Affected versions: - Apache Kylin 4.0.4 through 5.0.4 Description: Improper Neutralization of Special Elements used in an…

  18. Threat Intel via Help Net Security

    Fastfetch 2.70.0 changes how Disk free space is reported

    Fastfetch is a system information tool written mainly in C that runs on Linux, macOS, Windows 8.1 and later, Android and several BSDs. The fastfetch project removed…

  19. Threat Intel via SANS Internet Storm Center

    ISC Stormcast For Friday, October 16th, 2026 https://isc.sans.edu/podcastdetail/10140, (Fri, Oct 16th)

    (c) SANS Internet Storm Center. https://isc.sans.edu Creative Commons Attribution-Noncommercial 3.0 United States License.

  20. AI Security via Simon Willison

    sparqlite: SPARQL 1.1 inside SQLite, written in Rust

    Research: sparqlite: SPARQL 1.1 inside SQLite, written in Rust This research task is really an experiment in running Claude Code for web in "Ultracode" mode, as…

  21. Breaches via ransomware.live

    🏴☠️ N0n has just published a new victim : Company #75

    fintech payments · US | [PENDING EXPOSURE]