Search results

  1. TIMESLICE-SANDWICH: A GPU Side-Channel Attack Exploiting Time-Sliced Scheduling

    resource-sharing architectures. Kim Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:54 am

  2. SoK: Attack and Defense Landscape of Agentic AI Systems

    introduces complex security challenges that differ from traditional software systems. In this paper, we ... building secure agentic systems and advancing research in this critical area. Kim Paper (Prepublication) ...

    admin - April 21, 2026 - 10:54 am

  3. Silicon Heist: (Ransom) Attacks for Cloud FPGAs via Privilege Escalation

    neglected threat of unsecured low-level hardware components in cloud environments. Klix Paper ...

    admin - April 21, 2026 - 10:54 am

  4. End-to-End Encrypted Collaborative Documents

    solution is efficient enough to permit real-time collaboration. Knabenhans Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:54 am

  5. Security and Privacy Analysis of Tile's Location Tracking Protocol

    setting. Kumar Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:54 am

  6. Breaking Widely Deployed Perceptual Hash Functions: Black-Box Collisions in Apple NeuralHash and Microsoft PhotoDNA

    positives have serious consequences. Leblanc-Albarel Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:54 am

  7. SophOMR: Improved Oblivious Message Retrieval from SIMD-Aware Homomorphic Compression

    Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:55 am

  8. Heli: Heavy-Light Private Aggregation

    Texas at Austin This paper presents Heli, a system that lets a pair of servers collect aggregate ... less. Lehmkuhl Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:55 am

  9. Differential Trust: Dynamic Multi-Authority Anonymous Credentials with Epoch-Weighted Updates

    Remarkably, presenting a credential aggregated from 128 partial ones takes only 10.68 ms on average. Li Paper ...

    admin - April 21, 2026 - 10:55 am

  10. CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

    exacerbates privacy leakage. Li Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:55 am

  11. Shred-to-Shine Metamorphosis of (Distributed) Polynomial Commitments

    time than a multilinear variant of Kate–Zaverucha–Goldberg (TCC '13). Li Paper (Prepublication) ...

    admin - April 21, 2026 - 10:55 am

  12. E2E-AKMA: An End-to-End Secure and Privacy-Enhancing AKMA Protocol Against the Anchor Function Compromise

    deployment. Li Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 10:55 am

  13. On Evaluating the Robustness of Large Vision-Language Models via Untargeted Modality Alignment Breaking Adversarial Attack

    LVLM families, we derive valuable insights into strengthening the robustness of LVLMs. Li Paper ...

    admin - April 21, 2026 - 11:18 am

  14. BatchBoot: Fast Batched Bootstrapping for TFHE scheme and Practical Applications

    investigation. In this paper, we present BatchBoot, an efficient batched bootstrapping framework for TFHE that ... over the existing results (Wang et al., CCS'25). Li Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:18 am

  15. InstantOMR: Oblivious Message Retrieval with Low Latency and Optimal Parallelizability

    parallelism is constrained by reliance on BFV). Liang Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:18 am

  16. Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs

    enables a broader class of high-fidelity prompt-injection and command-execution attacks. Ling Paper ...

    admin - April 21, 2026 - 11:18 am

  17. The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again

    receiving acknowledgments and a $12,000 bug bounty. Liu Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:18 am

  18. Quantifying Large Language Model Attacks Through the Lens of Model Cognition

    propagate, and degrade within LLMs, enabling interpretable, inside-out alignment and diagnostics. This paper ... speech, discrimination, and other harmful text. Reader discretion is advised. Liu Paper (Prepublication) ...

    admin - April 21, 2026 - 11:18 am

  19. Cracks in the Walled Garden: Dissecting the Gray-Market of Unauthorized iOS App Distribution via Ad Hoc Sideloading

    multiple stakeholders. Liu Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:18 am

  20. Logos: Robust Sharding Blockchain With Fast Processing and Optimal Cross-Shard Overhead

    maintains 2.86× the throughput of Kronos, demonstrating strong robustness. Liu Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:18 am

  21. CuSafe: Capturing Memory Corruption on NVIDIA GPUs

    a negligible memory overhead of 0.3%. Lu Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:19 am

  22. Autonomy Comes with Costs: Detecting Denial-of-Service Vulnerabilities Caused by Resource Abusing in LLM-based Agents

    date, 15 CVE IDs have been assigned for these vulnerabilities. Luo Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:19 am

  23. SMASH: Scalable Maliciously Secure Hybrid Multi-party Computation Framework for Privacy-Preserving Large Language Models

    nonlinear operators and expensive share conversions. This paper presents SMASH, a highly scalable, ... between adversarial robustness and practical efficiency. Lv Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:19 am

  24. ZipPIR: High-throughput Single-server PIR without Client-side Storage

    that is competitive with state-of-the-art PIR protocols. Mahdavi Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:19 am

  25. CombiSan: Unifying Software Sanitizers for Comprehensive Fuzzing

    in a non-uniform manner. In this paper, we present CombiSan, a fuzzing-optimized sanitizer that ... running for significantly fewer CPU hours. Marini Paper (Prepublication) PDF ...

    admin - April 21, 2026 - 11:19 am

Pages