Product Information
Description
An annual survey of the cs.CR arXiv category, covering research published from September 2025 – August 2026. Built on a close-reading set of 100 papers and organised into 40 chapters, it maps the year by the field's research sub-directions.
Book framework (share of the year's output):
- Security of Large Language Models and Existing AI Agents (44.4%) — Analyses vulnerabilities, attacks, and defences for large language models and deployed AI agents.
- Recent Advances in Data Privacy, Threat Detection, and Secure Computing (44.0%) — Surveys data privacy protections, threat detection, and secure computing approaches across modern systems.
- Machine Learning Techniques for Modern Software Vulnerability Detection (7.7%) — Applies machine learning to detect vulnerabilities in modern software and to identify malicious patterns.
- Blockchain-Enabled Lightweight Security for IoT Devices (1.3%) — Uses blockchain and lightweight cryptography to secure resource-constrained IoT and decentralised systems.
- Semantic Watermarking for Trustworthy Generative Image Models (1.0%) — Studies semantic watermarking and provenance techniques to verify the authenticity of generated images.
- Systematic Evaluation and Benchmarking Practices (0.7%) — Develops benchmark suites and systematic evaluation practices to audit and compare security systems.
- Hardware Security Design and Measurement (0.4%) — Examines hardware-level security design, side-channel measurement, and physical-layer protections.
- Strong Formal Verification for Scalable Security Guarantees (0.3%) — Applies formal verification to provide strong, scalable security and auditability guarantees.
- Web Security Anomaly Detection and Vulnerability Management (0.1%) — Detects anomalies and manages vulnerabilities in web interfaces and online services.
Each sub-direction is covered across three chapters — how it framed its questions, the strength of its key findings, and its open debates and frontiers — so the reader gets a traceable picture of what this part of the field actually produced over the year.
