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.
1,372 papers, from 4 September 2026 to 5 November 2026: 1,372 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 67
Black-Box Membership Inference via Word-Level Probability Estimation
Membership inference attacks (MIAs) have emerged as critical tools for auditing privacy risks in large language models (LLMs), aiming to determine whether a given text was included in a model's…PEARL: A Task-Aware Framework for Evaluating Differentially Private Synthetic Educational Data
Personalized learning systems rely on real learner data, including performance, behavior, and demographic information, but these data are highly privacy-sensitive.Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting
In-context learning (ICL) jailbreaks reveal a critical vulnerability in multimodal large language models (MLLMs): harmful demonstrations in the prompt can induce unsafe outputs without modifying…MOLE: Detecting Insider Threats in AI Agents
Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltrate model weights, poison training data, or weaken release gates.AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories
LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter.CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records
Reasoning over privacy-constrained records requires combining structured attributes with evidence from free-text narratives.TrojanWorld: Backdooring World-Model Agents via Imagination Steering
World models increasingly serve as the predictive core of model-based reinforcement learning agents, enabling them to simulate future dynamics and reason over imagined trajectories before acting.AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing
Large language model (LLM) agents increasingly achieve long-horizon tasks by combining foundation models with explicit skills and implicit procedural knowledge acquired through execution.The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability
Several properties safety monitors are asked to certify, among them cross-tenant noninterference, sandbagging and evaluation awareness, are 2-safety hyperproperties, witnessed only by two executions.Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection
Anomaly-based intrusion detection systems in industrial control systems (ICS) and operational technology (OT) environments are increasingly required to meet formal resilience criteria: absorbed…Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration
This paper proposes a robust decentralized personalized federated learning method R-DPFL, that enables clients to reduce the impact of Byzantine attacks via robust neighborhood direction estimation…Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing
Large language model (LLM) based agents are increasingly applied to cybersecurity tasks such as vulnerability discovery and automated penetration testing.Privacy Leakage from a Thousand Words: Millipixel Location Recovery from Dot Maps
Dot maps, which visualize individual data points as dots over a geographic region, are widely used across diverse domains to represent spatial patterns in sensitive data.Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions
Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets, and time.Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain
AI coding assistants now select, install, and configure software, and attackers have exploited that position through invented package names, compromised maintainer accounts, and manipulated…VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities
The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies.Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints
Additional inference compute can increase the number of correctly resolved security-assurance tasks, but repeated success, unique coverage, accepted evidence, and operational protection are…An Empirical Measurement of Jailbreaking Evaluators
Expert evaluation of jailbreak responses is costly and difficult to scale, so the community increasingly relies on automated evaluators to determine whether an attack succeeds.Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge.CAPMAS: Capability-Based Delegation of Privileges in Multi-Agent Systems
Agentic systems require secure and efficient delegation of privileges across multiple collaborating agents.