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 20
Evidence-Grounded LLM-Assisted Android Mobile Forensic Reporting
Large language models can assist forensic report drafting, but fluent output does not ensure evidentiary reliability.Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin
To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user information across sessions.Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning.Private Evaluation of High-Dimensional Functions
We study differentially private black-box evaluation of arbitrary high-dimensional functions.Effective Construction of Feature Database of Fingerprinting Functions for Code-Clone SCA
In contemporary software development, the extensive adoption of third-party libraries has become standard practice to avoid reinventing the wheel.When Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems
Software quality has long rested on specifications that state what code must do, and on testing and verification that check that the code does it.Narratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in Bug Bounty Reports
Bug bounty platforms receive vulnerability reports faster than vendors can triage them, and Large Language Models (LLMs) are increasingly considered for assigning the Common Vulnerability Scoring…Collaborative Hand Drawing to Conceptualize Usable Privacy and Security Research Problems: Students' Perspectives (Extended Version)
In this paper, we explore students' perspectives on incorporating hand drawing to conceptualize usable privacy and security research problems.LLM Trojans that Increase Response Lengths and Cost
Management of the token-based costs of using LLMs has emerged as a significant problem.The Missing Compliance Class: LLM Graders That Collapse Jailbreak Success, and a Free Check
Jailbreak papers report an attack success rate, the share of responses that deliver the harmful request, and read it as a property of the target model.The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents
Can one sentence manipulate an agent's belief by targeting a single implicit warrant linking evidence to a conclusion?Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security
LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries.CAT-RAG: Improving Secure Code Generation with Category-Aware Agentic Retrieval
Despite rapid progress in LLM-based code generation, security vulnerabilities remain widespread, and retrieval-augmented code generation (RACG) can further amplify risk when retrieved knowledge is…Same Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets
Agent networks require reliable ways for requesting agents to verify where data is located, how it can be accessed, and whether the data received matches what the data owner made available.InterType: Breaking the Single-Function Barrier in Neural Binary Type Inference
Variable type recovery is a critical task in binary reverse engineering, enabling downstream applications such as vulnerability discovery, malware analysis, and security enforcement.How Intervention History Changes AI Agent Sabotage on Subsequent Tasks
AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions.Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction
Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) to remote providers exposes…Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks
Language-model watermarks can help identify model-generated text, encode provenance information, and detect post-generation edits.Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model must follow the…Provable Authority: A Protocol for Verifiable Authority Resolution and Control Across Human, Organizational, and Agentic Transactions
Payment systems authenticate users, devices, accounts, and cryptographic credentials, but a relying party, such as a counterparty, payment rail, marketplace, or autonomous agent runtime, generally…