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 48
"Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables
Large language model (LLM) assistants increasingly help users draft content for third-party recipients.LLM-Assisted Automatic Security Proofs for Cryptographic Protocols: How Far Are We?
Large language models (LLMs) have shown strong potential for assisting software and security analysis tasks, yet their effectiveness in cryptographic symbolic protocol verification remains…The Compiler May Read It, the Agent May Not: Keeping Part of a Research Code Away from a Coding Agent
The compiler must read modules a physics-based solver cannot build without; the coding agent must not read that intellectual property.Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents
Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and create persistent artifacts.SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents
Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management protocols, and…Succinct Arguments for QMA from Collapsing Hash Functions
We prove the existence of succinct arguments for QMA, assuming only the existence of collapsing hash functions.Distillation Defenses Easily Break After Reinforcement Learning
Distillation attacks copy the reasoning capabilities of closed-source large language models, allowing bad actors to replicate state-of-the-art performance at low cost.Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries.Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a subset under a finite budget.MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
Agent skills are shareable packages of procedural instructions, tools, and examples.Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection
Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template.PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents
While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources.Multi-Class, Multi-Tier Network Intrusion Detection: A Comprehensive and Reproducible Benchmark
Machine learning (ML) and deep learning (DL) have dominated Intrusion Detection System (IDS) research in recent years.Why Backdooring Neural Networks is so Easy?
Securing modern AI systems against backdoor attacks remains an open challenge and requires fundamentally principled estimates of the adversary's budget -- the poison fraction $π$ and trigger…Render Before Reading: Visual Rendering as a Prompt Injection Defense
Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior.Privacy-Friendly Cohort Determination: Sealed, CSP-Independent In-Browser ML Inference of Professional Segments for Identity-Less Advertising
B2B advertising targets a viewer's professional attributes (employer size and industry, function, seniority) and has obtained them by matching identities across sites.Adversarial Debiasing of Machine Learning Models for Enhanced Network Security against DDoS Attacks
Distributed Denial of Service attacks are a growing threat to network infrastructure, and new techniques, including the use of generative AI, make them harder to detect.An Empirical Study and Assessment of EU AI Act Compliance Checkers
The EU AI Act introduces extensive compliance requirements for organizations that develop, deploy, or integrate AI systems.DecoyTrace: Toxic Decoys for Active Defense in Decentralized Federated Learning
Decentralized Federated Learning (DFL) eliminates the central aggregation server, reducing the single point of observation that traditional defenses against attacks rely on.Calibrating One-Round Membership Inference with Neighbors
The state-of-the-art Membership Inference (MI) methods calibrate their signal separately for each example using reference models, auxiliary models trained to exclude the target.