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 2
Explainable Anomaly Detection in 5G Networks through Continuous Time Graphs
5G networks increasingly resemble distributed systems in their design.Analysis of Local Open-Weight LLM Agents on Vulnerability-Reproduction Tasks
Open-weight language models that fit on a single consumer GPU are becoming capable on a growing range of tasks, and they matter because they can run locally without sending the code to a hosted…Clear Human Web: Where a Person Vouches for Every Client
The web cannot tell whether a request comes from a person or from a program.A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code
Large language model (LLM) coding assistants and agents construct a repository context before generating code.CoRTeC: A Differentially Private Release for Synthetic Tabular Data, Decodable by Any Generator
The records that could train the most useful models, such as a hospital's patient files, are often the ones an institution cannot share.A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks
The protection of mature, multi-stage Face Recognition Systems is crucial to system providers.Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors.Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models
Large language models (LLMs) undergo safety alignment to prevent harmful generations, yet they remain vulnerable to jailbreak attacks.Signed, Sealed, Leaked: Trust Beyond Signature for MCP Toolchains
AI agents rely on third-party tools, such as Model Context Protocol (MCP) servers, whose publishers can be authenticated and whose execution can be restricted by runtime security policies.Global Surveillance Under the Lens: Reconstructing Passive Dolev-Yao Intruders
Global surveillance systems record large volumes of network traffic for retrospective analysis, but packet captures alone reveal little about protocol-level semantics.SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection
Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker.ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking
Existing attacks treat evasion as a removal problem: they erase the watermark, relying on detector access or on speech data that is hard to collect, such as paired clean-watermarked or clean target…Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs
Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors can read to monitor embodied safety.When Debate Amplifies Risk: Social-Bias Vulnerabilities in Multi-Agent Safety Deliberation
Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process…Gaussian Difference Dynamics: Breaking the $2^{n/2}$ Barrier for the Shortest Vector Problem and Discrete Gaussian Sampling
We give classical randomized algorithms in a word RAM model that break the $2^{n/2}$ barrier for both discrete Gaussian sampling (DGS) and the Shortest Vector Problem (SVP).CloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion
Finite element method (FEM) solvers are foundational to scientific and engineering simulation, yet their susceptibility to \emph{efficiency attacks} remains largely unexplored.Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents
LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with…A Security Analysis of Verifiable Credential Verification Pipelines: Attack Surface Arising from JSON-LD/RDFC Canonicalization Compared with SD-JWT VC and mdoc
We evaluate, at implementation level and under an explicit threat model, the verification pipelines of three Verifiable Credential (VC) formats: SD-JWT VC; the W3C Verifiable Credentials Data Model…Perseus: A Full-Stack System for Homomorphic Model Inference
Large Language Models (LLMs) have made it exceptionally convenient for users to send their private data to model providers, which process them in plaintext.Residual Attribute Leakage Is an Interface: Auditing Privacy Evaluation After Text De-identification
A privacy evaluation of de-identified text asks a language model (the adversary) to guess a person's protected attribute.