本日紹介した論文の一覧
Improving Statistical Privacy by Subsampling
http://arxiv.org/abs/2504.11429v1
DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
http://arxiv.org/abs/2504.11358v1
The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to
Fine-Print Injections
http://arxiv.org/abs/2504.11281v1
Slice+Slice Baby: Generating Last-Level Cache Eviction Sets in the Blink
of an Eye
http://arxiv.org/abs/2504.11208v1
R-TPT: Improving Adversarial Robustness of Vision-Language Models
through Test-Time Prompt Tuning
http://arxiv.org/abs/2504.11195v1
Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
http://arxiv.org/abs/2504.11182v1
Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails
http://arxiv.org/abs/2504.11168v1
KubeFence: Security Hardening of the Kubernetes Attack Surface
http://arxiv.org/abs/2504.11126v1
A Unified Hardware Accelerator for Fast Fourier Transform and Number
Theoretic Transform
http://arxiv.org/abs/2504.11124v1
Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image
Models
http://arxiv.org/abs/2504.11106v1
FLSSM: A Federated Learning Storage Security Model with Homomorphic
Encryption
http://arxiv.org/abs/2504.11088v1
Leveraging Vertical Public-Private Split for Improved Synthetic Data
Generation
http://arxiv.org/abs/2504.10987v1
Improved MST3 Encryption scheme based on small Ree groups
http://arxiv.org/abs/2504.10947v1
Cartesian Merkle Tree
http://arxiv.org/abs/2504.10944v1
PT-Mark: Invisible Watermarking for Text-to-image Diffusion Models via
Semantic-aware Pivotal Tuning
http://arxiv.org/abs/2504.10853v1
How to Enhance Downstream Adversarial Robustness (almost) without
Touching the Pre-Trained Foundation Model?
http://arxiv.org/abs/2504.10850v1
FlexiContracts: A Novel and Efficient Scheme for Upgrading Smart
Contracts in Ethereum Blockchain
http://arxiv.org/abs/2504.10811v1
なお、ポッドキャスト内で紹介する内容は、各論文の概要を日本語で解説したもので、論文概要の著作権は論文著者に帰属します。
]]>