Search Results

Refine Results
  1. Cover Image

    PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  2. Cover Image

    The Deepfakes We Missed: We Built Detectors for a Threat That Didn't Arrive

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  3. Cover Image

    A microservices-based endpoint monitoring platform with predictive NLP models for real-time security and hate-speech risk alerting

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  4. Cover Image

    AccLock: Unlocking Identity with Heartbeat Using In-Ear Accelerometers

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  5. Cover Image

    Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  6. Cover Image

    IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  7. Cover Image

    Five Attacks on x402 Agentic Payment Protocol

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  8. Cover Image

    Behavioral Integrity Verification for AI Agent Skills

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  9. Cover Image

    Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  10. Cover Image

    Deanonymizable Scoped Linkable Ring Signatures

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  11. Cover Image

    Quantitative Semantics for Jumping Automata

    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  12. Cover Image

    HySecTwin: A Knowledge-Driven Digital Twin Framework Augmented with Hybrid Reasoning for Cyber-Physical Systems

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  13. Cover Image

    Cochise: A Reference Harness for Autonomous Penetration Testing

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  14. Cover Image

    Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  15. Cover Image

    Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  16. Cover Image

    PhishSigma++: Malicious Email Detection with Typed Entity Relations

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  17. Cover Image

    Convolutional-Neural-Networks for Deanonymisation of I2P Traffic

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  18. Cover Image

    SoK: Unlearnability and Unlearning for Model Dememorization

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  19. Cover Image

    LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues

    Published in ArXiv cs.CL Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:
  20. Cover Image

    The Algorithmic Caricature: Auditing LLM-Generated Political Discourse Across Crisis Events

    Published in ArXiv cs.CL Recent Papers (2026)
    Get full text
    Full Text Available
    Access Full Text at Repository
    Online Article RSS Article
    Save to List
    Saved in:

Search Tools: