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 30
LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override…Local Sensitivity in Exponential Selection: Failure Modes and Valid Calibrations
Selection is a task that chooses one element from a finite public candidate range to maximize a data-dependent score.Protecting CPU AI On Edge TEEs: WebAssembly's Promise and Practical Challenges
AI models on edge hardware contain important intellectual property (IP), but an adversary can steal it when they achieve root access.Could LLM Watermark Detection be Public?
Watermarking large language models is popular for tracing chatbot and agentic outputs, yet detectors remain unreleased since exposing them could let attackers do targeted edits with the detector's…Poster: A Preliminary Study of LLM Distillation Inference
Unauthorized model distillation, in which a model is trained on the outputs of a proprietary large language model (LLM), is a growing threat to model providers.Verification with Transfer: Exact Information Frontiers and Their Price in Calls
A verifier that accepts or rejects whole answers reveals little: under a flat prior over $k$-bit answers, zero error needs $2^k-1$ verifications.ReSI: Recursive Safety Improvement toward Resistant and Resilient AI
Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to practice, posing both challenges and opportunities…Improved Local Leakage Resilience of Shamir Secret Sharing and Worst-Case Optimal Polynomial Intersection
We study two problems: Local Leakage Resilience (LLR) for Shamir secret sharing, and worst-case Optimal Polynomial Intersection (OPI).From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope.Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller
Backdoor Attacks on Large Language Models (LLMs) typically follow a trigger-response pattern, where satisfying a trigger condition activates a single terminal behavior.PVBRF-ID: Private, Verifiable and Byzantine-Robust Federated Intrusion Detection for Oilfield Enterprise Networks
Federated learning allows dispersed oilfield sites to train a shared intrusion detector without pooling network traffic, yet its aggregation step forces a choice between privacy and robustness.Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing
Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence.VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks.SAGE: Efficient Protected Vision-Language Inference on Smart Glasses
Smart glasses are a promising platform for vision-language assistants, but private split inference remains expensive: protecting visual representations before transmission does not remove the cost…Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions.Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files
Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation, yet the security risks of this pipeline…Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense
Policy-based reinforcement learning (RL) approaches have produced promising results for autonomous cyber defense; however, they are sample-inefficient in settings where defenders must respond under…Secure-CUA: Controlling Untrusted Influence in Computer-Use Agents
Computer-use agents (CUAs) perform tasks across applications (such as desktops, mobile apps, and web browsers) by observing graphical interfaces and issuing commands such as clicks and keystrokes.Constitution-Guided Watermarking
Watermarking enables language model providers to identify text generated by their models.MARS: Malware Analysis with Rule-Based Scoring of LLM Claims
Large language models can triage malware through direct verdicts or behavioral claims scored by an external policy.