Security & Cryptography · Computer Science & AI
Cryptography & Security
The newest papers in Cryptography & Security that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
1,371 papers, from 4 September 2026 to 5 November 2026: 1,371 arXiv preprints.
Get the few papers worth your time in Cryptography & Security every morning.
Follow Cryptography & Security and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 6
GESIS Surf: An Open-Source Infrastructure for Privacy-Preserving Longitudinal Web Browsing Data Collection
Understanding how people navigate digital media environments requires behavioral data beyond survey self-reports.DeepWeave: Weaving Neural and Symbolic Evidence for ML-Based Network Intrusion Detection System
Machine learning-based network intrusion detection systems can recognize complex traffic patterns, but often require substantial labelled attack data, degrade under deployment shift, and provide…Simple Features Beat Most AI Control Monitors
AI control relies on monitors to catch a capable model that sabotages its work.From Training Exposure to Membership Evidence: A Controlled Study of OLMo 2
Yet most membership-inference (MI) evaluations on language models collect members and non-members after the fact, so success may reflect distribution shift and failure is inconclusive.Reparo: Synthesizing and Validating Access Control Policies
Writing correct access control policies for software applications is difficult because it requires expertise in the authorization language and a thorough understanding of the application's…What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer
Detectors can flag hijacked large language model (LLM) agents from the traces of the tools they call.Exploring Bad Minima in Transfer Learning
Transfer learning is a highly successful learning paradigm in deep learning which leverages knowledge from one task and applies it to another.How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces
Large language model (LLM)-based agents interact with external tools through protocols such as the Model Context Protocol (MCP), producing tool-call traces that may expose behavioral signals about…On-Chain Behavioral Signatures for Classifying Centralized Exchange Addresses on Ethereum Using Proof-of-Reserves
Centralized exchanges (CEXs) are key gateways between traditional finance and digital asset markets, yet identifying their blockchain addresses remains challenging.SecPO: Principled Adversarial Training for Prompt Injection Security
Recognized as a top threat to AI agents, prompt injection allows instructions from untrusted data (email, documents, websites) to manipulate the agent's operation.Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches
In many practical deployments of Differentially Private Stochastic Gradient Descent (DP-SGD), the server processes data in batches.Humanized but Still True? Auditing Facts and Detection in AI-Text Humanizers
AI "humanizers" rewrite machine-generated text so that detectors classify it as human-written.When appearance and motion disagree: evaluating class--motion consistency against disguised uncrewed surface vessels
Defense systems for maritime assets must distinguish approaching benign craft from uncrewed surface vessels (USVs) with sufficient warning to act.Spoofing the Latent State: Imperceptible Goal-Image Attacks Derail Planning in LeWorldModel
Joint-embedding predictive architectures (JEPAs) have recently emerged as general-purpose visual world models for control.Usable String Matching by Humans through Overlaid Presentation
We explore the ability of humans to compare strings, an error-prone activity which occurs in critical contexts (e.g., bank wire transfers), where it is not always possible to trust a machine to help.PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication
When one AI agent tells another that "the tests passed" or "a person approved this refund", the receiver has only the sender's word.Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection
Self-evolving personal agents act for users and learn from user feedback.DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3
Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications provide abundantly.Unlocking with the Heart: Investigating User Perceptions of ECG-Based Biometric Authentication
Password-based authentication remains challenging for many users, especially for those who face usability and accessibility issues.REALM: Identifying Minimal Task Assets for LLM Agents
Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires.