Latest news

Advertisement
  1. Vulnerabilities via arXiv cs.CR

    When Core-Network Elements Become Reachable: Field-Level Exploitability Analysis in Diameter

    arXiv:2610.22943v1 Announce Type: new Abstract: The increasing exposure of cellular core-network elements to public networks has turned Diameter signaling interfaces…

  2. AI Security via arXiv cs.CR

    SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval

    arXiv:2610.22959v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized…

  3. Breaches via arXiv cs.CR

    Surprise Masking: Private Data Filtering with Model Likelihoods

    arXiv:2610.22988v1 Announce Type: new Abstract: Data useful for language model (LM) training can contain private or unwanted information that is at risk of being learned…

  4. AI Security via arXiv cs.CR

    ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack

    arXiv:2610.23030v1 Announce Type: new Abstract: Despite extensive safety alignment, large language models remain vulnerable to jailbreak attacks. Existing…

  5. Vulnerabilities via arXiv cs.CR

    Aspire: Practical Batch Queries on Dynamic Encrypted Database with Full Leakage Suppression

    arXiv:2610.23057v1 Announce Type: new Abstract: Leakage-abuse attacks against encrypted database systems exploit semantic leakage and pose a severe threat to the…

  6. AI Security via arXiv cs.CR

    When Approval Becomes Execution: Authorization-Grounded Workflow Attacks on Tool-Using Agents

    arXiv:2610.23077v1 Announce Type: new Abstract: Tool-using language-model agents increasingly rely on local services for document access, approval management, and…

  7. AI Security via arXiv cs.CR

    Cryptographically Secure Agent-to-Agent Communication in Multi-Agent Systems

    arXiv:2610.23078v1 Announce Type: new Abstract: Multi-agent systems (MAS) comprise AI agents that collaborate or compete to perform complex, distributed tasks. Their…

  8. Breaches via ransomware.live

    🏴☠️ Helix has just published a new victim : American Campus

    American Campus records. Yearly revenue ~$1 billion yearly. GoFile links and passwords unlock in 6 hours.

  9. Advertisement
  10. Breaches via ransomware.live

    🏴☠️ N0n has just published a new victim : Finzly Corp

    fintech payments · US | Network configuration and access secrets for payment infrastructure; Cloud environment topology and access keys | [NOT PAID — EXPOSED]

  11. AI Security via Horizon3.ai

    Horizon3 expands in Singapore to accelerate AI‑native proactive security across Southeast Asia

    Strategic investments from EDBI and SG Growth Capital to support regional growth and continuous, evidence‑based cyber resilience SINGAPORE – October 19, 2026 – Horizon3…

  12. Vulnerabilities via Security Affairs

    16-Year-Old Broadcom Wi-Fi Bug Lets Attackers Take Over Routers Without a Password

    A Broadcom Wi-Fi flaw dating back to 2010 allows attackers within Wi-Fi range to execute code on vulnerable routers without authentication. Researcher Quentin Kaiser…

  13. Breaches via ransomware.live

    🏴☠️ N0n has just published a new victim : Company #93

    healthcare support services · United States | [PENDING EXPOSURE]

  14. Breaches via Hudson Rock

    Infostealers Weekly Report: 2026-10-12 – 2026-10-19

    InfoStealers Weekly Report – In this comprehensive report, we provide you with valuable insights into the most pressing threats facing organizations today. As…

  15. AI Security via Datadog Security Labs

    Putting models to the secure coding test: Security rules

    We tested Sonnet 5, Composer 2.5, and GPT 5.5 using set security rules to see whether using them produces measurably more secure code.

  16. AI Security via AI Incident Database

    PJF move ação civil pública contra nova central estadual de regulação de leitos na saúde

    Mãe de gêmeos, moradora de Mar de Espanha, morreu durante saga em busca de UTI neurológica A substituição do sistema de regulação de leitos na saúde SUSFácil pela…

  17. AI Security via AI Incident Database

    Psicóloga morre após esperar cinco dias por vaga de UTI em MG; família questiona sistema que distribui leitos

    Rebeca Cardoso Tenente Molina, de 32 anos, procurou atendimento devido a pedras na vesícula, teve uma rápida piora no quadro clínico e precisava ser transferida…

  18. AI Security via AI Incident Database

    Mobilisation lycéenne : quand les images «améliorées» par l’IA génèrent des fausses pistes

    Mobilisation lycéenne : quand les images «améliorées» par l’IA génèrent des fausses pistes Dans le cadre du mouvement lycéen, de nombreux internautes utilisent des…

  19. AI Security via Simon Willison

    llm-tools-datasette 0.1.1

    Release: llm-tools-datasette 0.1.1 When I switched LLM over to httpx2 in LLM 0.33 I forget that this would break any plugins which used httpx without directly depending…

  20. Breaches via ransomware.live

    🏴☠️ N0n has just published a new victim : Amagi Media Labs

    media technology / broadcast playout · United States | Network and device configuration files from a US broadcast playout site; Internal network maps of the site | [NOT…

  21. Breaches via ransomware.live

    🏴☠️ N0n has just published a new victim : Company #92

    IT services · South Korea | [PENDING EXPOSURE]