illustration of lock, four asterisks and a shield with a fingerprint on it on a green gradient background

Security, privacy, & cryptography

Developing technologies that protect data, preserve privacy, and build trustworthy computing systems.

Diagram showing the process of verifying cryptographic code. An algorithm from a standard is converted into a formal specification, while Rust code is converted into a code model. The specification and code model are then compared through proof and verification steps.

Verifying Rust cryptography in SymCrypt, from standards to code

Three white line-style icons centered on a textured blue-to-green gradient background: a shield, a checkmark inside a circle, and an ID card with a user silhouette—representing security, verification, and digital identity.

Vega: Zero-knowledge proofs for digital identity in the age of AI

Project Ire | | three white line icons on an abstract purple background | greater than / less than icon, search icon, shield icon

Ire identifies another LOTUSLITE specimen

Social Reasoning Bench | four icons on a blue to green gradient | person icon, chat bubble icon, chart icon, checklist icon

SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests

当前选择

排序方式: 最新

清除选择

在这些结果中搜索

内容类型

发布日期

论文与出版物

Decaf: A privacy preserving speech codec using speaker disentanglement and canonical voice conversion

Md Shakhrul Iman Siam, D. Sharma, S. Kruchinin, Peter Skala

September 2026

arXiv | September 2026

论文与出版物

Scaling Verification of Cryptographic Software with Aeneas, Rust, and Lean

Ho Son, Cédric Fournet, Jonathan Protzenko, Michael Naehrig, Joshua Clune, Patrick Longa, G. Boisseau, Fernando Leal Sánchez, Aymeric Fromherz, Antoine Delignat-Lavaud

September 2026

arXiv | September 2026

论文与出版物

SpecGuard: Inference-Time Backdoor Detection For Free

Wen Rui, Ahmed Salem, Andrew Paverd, M. Russinovich, Li Zheng

September 2026

arXiv | September 2026

论文与出版物

On the Impact of Anonymization on the Performance of Large Language Models

Tobias Deußer, Max Hahnbück, L. Sparrenberg, T. Uelwer, Christian Bauckhage, R. Sifa

September 2026

arXiv | September 2026

论文与出版物

NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces

Zahra Tarkhani, Georgios Akkogiounoglou, Lorena Qendro, Isabel Tscherniak, Anil Madhavapeddy

September 2026

arXiv | September 2026

论文与出版物

Towards Standardized Evaluation of GPU Memory Safety with GMSBench

Saurabh Singh, Jaewon Lee, Seonjin Na, Hyesoon Kim Georgia Institute of Technology, Microsoft, Nvidia

September 2026

arXiv | September 2026

论文与出版物

Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces

Roy Weiss, B. Konstantinov, Eitam Sheetrit, Tomer Simon, Yisroel Mirsky

September 2026

arXiv | September 2026

论文与出版物

Conformal Prediction for Offensive Security

Giovanni Cherubin

September 2026

arXiv | September 2026

论文与出版物

Pirateship: Append-Only Ledgers for (Mostly) Trusted Execution Environments

Shubham Mishra, João Gonçalves, Chawinphat Tankuranand, Neil Giridharan, Natacha Crooks, Heidi Howard, Chris Jensen

2026 Symposium on Operating Systems Principles | September 2026

论文与出版物

The anatomy of a resilient phishing detector: an in-depth analysis of a transformer’s interpretability, causality, and robustness

V. D, Geetha Dayalan, Abhay Bhandarkar

Frontiers in Computer Science | August 2026

Security, privacy, & cryptography

高亮