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 7
CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation
Digital watermarking offers a promising solution by enabling user-level traceability, yet existing methods remain difficult to deploy at scale, hindered by costly model retraining or detection, poor…AgentHeal: Evaluating Goal-Preserving Resource Recovery of Web Agents under Access Barriers
Large language model (LLM) agents have demonstrated strong capabilities in automating complex information-seeking and transactional tasks across the open web.ARBITRA: Robust Document-Level ATT&CK Extraction via Multi-Expert Argumentation
Cyber threat intelligence (CTI) reports describe adversary behavior in natural language, but converting them into structured MITRE ATT&CK mappings remains difficult: existing methods decompose…Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection
Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requires training on sensitive data from multiple organizations, putting privacy…When Static Reachability Says No: Checking Joern-Based Negative Verdicts for Python Against Execution
A negative reachability verdict removes a finding from human review.Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy
Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication.Hardware-Aware Model Inversion in Memristive Spiking Neural Networks
Hardware-accelerated spiking neural networks (SNNs) implemented on memristive crossbar arrays offer significant gains in energy efficiency, while device variability and analog noise are sometimes…InferD: A Honeypot Framework for AI Inference Infrastructure
Large language model serving stacks, commercial inference APIs, vector databases, and agent orchestration gateways are now ex- posed on the public internet and indexed by commodity scanners within…Surprise Alone Learns Lies: Evidence-Gated Continual Learning for LLMs from Streaming Claims
Continual learning methods for large language models increasingly decide what to learn by surprise, keeping the inputs the model finds least predictable.ExploreRepair: Evidence-Specialized Agents for Vulnerability Repair under Information Constraints
Automated vulnerability repair must often operate with incomplete vulnerability information: developers may lack an accurate vulnerability classification or a provided proof-of-vulnerability (PoV)…DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning
As network scale and uncertainty complicate automated penetration testing, reinforcement learning (RL) environments must support controlled evaluation under defensive and non-stationary conditions.Understanding and Mitigating Role Spoofing in LLMs
Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models.Deep Learning Based Behavioral Drift Modeling for Continuous Biometric Authentication
This research proposes a two-level keystroke dynamics authentication system that provides defense-in-depth security through continuous behavioral drift monitoring.Efficient Scalable Oversight via Rewinding
Scalable oversight asks how a weak verifier can check the outputs of computations performed by more powerful AI systems.TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same…Difficulty Calibration Across Time for Membership Inference in Diffusion Models
Modern diffusion models are trained on massive datasets that often include copyrighted or private images.PrivacyFlow: Privacy in AI Agents through Information Flow Analysis and Consequence-Aware Risk Management
Autonomous LLM agents executing multi-step workflows over personal data often misalign with user privacy expectations and leak sensitive, out-of-context information.Characterizing LLM Agent Behaviors in Module Shadowing Environments
LLM agents operating in untrusted workspaces face the risk of untrusted code execution during routine tasks, yet final reports and workspace states alone cannot reliably establish whether execution…MetaVul: Agentic Harness Discovery for Vulnerability Detection
LLM agents are increasingly used to automate vulnerability detection, but reliable detection is challenging because agents must distinguish subtle, security-relevant fixes from benign code variation.RiskyPy: Toward Model-Calibrated Prompt Generation for Joint Security and Functionality Evaluation of LLM-Generated Code
Evaluating approaches that improve the security of LLM code generation requires datasets that jointly assess security and functionality and remain adapted to the capabilities of the models being…