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 60
(Don't) Trust, but (Don't) Verify: Developers' Attention to Security in AI-Generated Code
AI coding assistants are rapidly transforming software development, but are known to produce insecure code.Loopjacking: Hijacking Human-in-the-Loop Approval
Human approval is often treated as the last security boundary before an agent executes a consequential operation.QuanText: Protecting Dataset-Level Secrets in Textual Data Sharing
Natural-language datasets support many downstream applications and research studies, but releasing text can reveal sensitive global properties of the underlying data source, such as the proportion…FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection
Graph anomaly detection aims to identify graph structures (e.g., nodes, edges, or subgraphs) that deviate significantly from expected patterns, which supports critical applications in fraud…PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs
AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, automated testing unaffordable for the smaller…"Your Robot Was Trained on a Lie": Collision Mesh Poisoning Attacks on Robotic Manipulation
Learning-enabled robotic manipulation increasingly relies on robot simulators for policy training and evaluation before real-world deployment.Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI
Agentic AI systems plan, invoke tools and act with limited supervision; they are now both the subject of audits and, increasingly, the auditor.A GAN-Based Framework for Robust DDoS Attack Detection
The availability and consistency of online services remain vulnerable due to Distributed Denial of Service (DDoS) attacks.Autonomy in Check: Governor-Mediated Adaptive Security at the Edge
Adaptive security at the network edge increasingly relies on automated planners, including rule-based controllers, learned policies, and LLM-assisted agents, that translate observations into…AIJon: Automated Generation of Annotations for Fuzzing
Modern fuzzers use code coverage as feedback to guide their exploration which has proven to be an effective strategy for driving exploration.SEEK: Secure and Efficient Encrypted Keyword Search For Privacy-Preserving Messaging Protocols
Encrypted communication protects sensitive user data but can facilitate harmful or unlawful exchanges, creating a trade-off between detecting dangerous messages and preserving end-user privacy.Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery
How does a multi-agent system evolve from a local deviation into collective loss of control?A Global Readiness and Sovereignty Capability Model for Post-Quantum Cryptography Migration
Cryptographic dependence predates the quantum era, but the migration to post-quantum cryptography (PQC) opens a rare window to reshape it, because the algorithms, implementations, hardware, and…MiST: Mid-Training LLMs for Cybersecurity
Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs.Echo: Learning-based Matching Decompilation using Trusted Back Translation
Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust.ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions
Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report.Securing quantum error correction against misleading advice from AI agents
Can an attacker turn influence over an artificial intelligence (AI) adviser into a harmful quantum error-correction update?PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows
AI-mediated platforms coordinate work through LLM agents acting for different principals.AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment
Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket refusal on benign requests and polished but…MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs
LLM coding agents now generate complex programs at a scale that makes thorough human review increasingly difficult, raising the risk of safety and security failures.