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 39
The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs
Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enforced safeguards.EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources.LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization
Digital watermarking supports source attribution for AI-generated images, but its reliability depends on resistance to removal attacks.Defense-in-Depth at the Perception-Reasoning Interface of LLM-Centric Agentic UAV Swarms
Large Language Models (LLMs) increasingly support Uncrewed Aerial Vehicle (UAV) swarm operations such as data collection scheduling, where the model reads structured sensor reports and decides which…Quantifying Ethereum Energy Consumption via Network Mapping
Ethereum's electricity use fell by about 99.95% after the move from proof of work to proof of stake.Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents
LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchmarks.Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation
Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones.PrivDev: Mapping Static-Analysis Data Types to DPV
Static-analysis scanners can identify personal-data types in source code, but they lack mechanisms to connect these findings to standardized privacy vocabularies.Reasoning Models Are Accurate but Unsound on Identification
A reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers a nonidentifiable one.Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming…Constant-Rate Certified Deletion
We present a unified framework for upgrading a broad class of cryptographic primitives to support constant-rate certified deletion.Quantum Fire with Delegated Cloning
Quantum fire is a recently introduced cryptographic primitive consisting of efficiently preparable quantum states, called \emph{flames}, that admit efficient cloning but resist efficient…PoCoFL: POlicy-COmpliant Federated Learning
Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping training data local to participating clients.Unitary complexity in polynomial space
We show that if quantum commitments exist, then either there is no polynomial-time solution to the unitary synthesis problem, or $\mathsf{BPP} \neq \mathsf{NEXP}$.From Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review
Design-level security weaknesses can arise from requirements, trust assumptions, missing controls, and data flows before implementation begins.Beware EviLLM: Enabling Vulnerability Injection via Large Language Models
Advances in large language models (LLMs) have enabled AI-driven code generation from natural language specifications, introducing new attack surfaces for injecting vulnerabilities into software.Localize-and-Detect: Auditing Task-Level Poisoning in Instruction-Tuned Models
Instruction fine-tuning adapts a pretrained language model to follow instructions by training it on instruction--response pairs from a collection of tasks, such as summarization and question…What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document
Split learning lets a client train a language model on a server without sending its text.AuraForge: Scaling Security Supervision for Training Coding Agents
Coding agents are now proficient enough to generate complex software applications from a single prompt.DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text
Robust detection of AI-generated text under deployment conditions is challenging: distribution shifts across domains and generators, adversarial perturbations of the input surface, and the absence…