ArXiv TLDR
← All categories

Cryptography & Security

Research on AI security, adversarial attacks, privacy, and cryptographic methods.

cs.CR · 505 papers

Engineering Robustness into Personal Agents with the AI Workflow Store

This paper introduces an AI Workflow Store to integrate rigorous software engineering into AI agents, creating robust, reusable workflows instead of brittle on-the-fly systems.

2605.10907May 11, 2026Roxana Geambasu, Mariana Raykova, Pierre Tholoniat +3

Private Information Retrieval With Arbitrary Privacy Requirements for Graph-Based Storage

This paper redefines Private Information Retrieval (PIR) privacy for graph-based storage, enabling flexible, arbitrary requirements.

2605.10879May 11, 2026Mohamed Nomeir, Shreya Meel, Sennur Ulukus

Local Private Information Retrieval: A New Privacy Perspective for Graph-Based Replicated Systems

This paper introduces "local PIR" for graph-replicated systems, showing significant communication efficiency gains by redefining user privacy.

2605.10872May 11, 2026Shreya Meel, Mohamed Nomeir, Sennur Ulukus

BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data

BEACON is a large, multimodal dataset from competitive Valorant gameplay for continuous authentication and behavioral fingerprinting research.

2605.10867May 11, 2026Ishpuneet Singh, Gursmeep Kaur, Uday Pratap Singh Atwal +3

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

This paper introduces a new evaluation protocol for AI pentesting agents, shifting from task completion to realistic vulnerability discovery.

2605.10834May 11, 2026Pedro Conde, Henrique Branquinho, Valerio Mazzone +3

Democratizing Measurement of Critical Mobile Infrastructure: Security and Privacy in an Increasingly Centralized Communication Ecosystem

This paper introduces open-source measurement platforms to independently analyze the security and privacy of complex mobile communication ecosystems, including cellular and OTT services.

2605.10812May 11, 2026Gabriel K. Gegenhuber

Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights

An evaluation of domain-adapted LLMs for STRIDE threat modeling reveals inconsistent performance and fundamental limitations, urging task-specific reasoning.

2605.10808May 11, 2026Saba Pourhanifeh, AbdulAziz AbdulGhaffar, Ashraf Matrawy

LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges

A review of LLMs in hardware design, covering their capabilities, introduced vulnerabilities, and essential security countermeasures.

2605.10807May 11, 2026Johann Knechtel, Ozgur Sinanoglu, Ramesh Karri

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing

Frontier language models involuntarily leak secret information thematically in their writing, even when instructed not to, posing a privacy risk.

2605.10794May 11, 2026Ari Holtzman, Peter West

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

LITMUS benchmarks LLM agent behavioral jailbreaks in real OS environments, revealing critical safety gaps and a new "Execution Hallucination" phenomenon.

2605.10779May 11, 2026Chiyu Zhang, Huiqin Yang, Bendong Jiang +8

MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study

MATRA is a threat modeling framework for agentic AI systems, assessing risks and quantifying how architectural controls reduce attack blast radius.

2605.10763May 11, 2026Tim Van hamme, Thomas Vissers, Javier Carnerero-Cano +4

AutoSOUP: Safety-Oriented Unit Proof Generation for Component-level Memory-Safety Verification

AutoSOUP automates component-level memory-safety verification using Safety-Oriented Unit Proofs and a hybrid LLM-as-function-call architecture.

2605.10712May 11, 2026Paschal C. Amusuo, Ricardo Calvo, Dharun Anandayuvaraj +5

diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories

diffGHOST is a diffusion model that generates privacy-preserving synthetic mobility trajectories by mitigating memorization in a segmented latent space.

2605.10647May 11, 2026Florent Guépin, Cheick Tidiani Cisse, Denis Renaud +2

Re-Triggering Safeguards within LLMs for Jailbreak Detection

This paper introduces an embedding disruption method to re-trigger LLM safeguards, effectively detecting and defending against jailbreak attacks.

2605.10611May 11, 2026Zheng Lin, Zhenxing Niu, Haoxuan Ji +2

Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing

This paper reveals a new vulnerability where hidden branding in images can be re-rendered by generative AI models during editing, even without explicit prompts.

2605.10600May 11, 2026Desen Sun, Jason Hon, Howe Wang +3

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

DR-Smoothing offers a guaranteed defense against LLM jailbreaking attacks by disrupting and rectifying prompts, balancing safety and helpfulness.

2605.10582May 11, 2026Zheng Lin, Zhenxing Niu, Haoxuan Ji +1

Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims

Acceptance Cards introduce a four-diagnostic standard to rigorously evaluate safe fine-tuning defenses, revealing flaws in existing methods like SafeLoRA.

2605.10575May 11, 2026Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

SoK: A Systematic Bidirectional Literature Review of AI & DLT Convergence

This paper systematically reviews AI and DLT convergence, classifying contributions and identifying neglected research areas and critical challenges.

2605.10515May 11, 2026Ali Irzam Kathia, Yimika Erinle, Abylay Satybaldy +3

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements

This paper introduces UPAttack, demonstrating how usability requirements can force LLMs to generate insecure code, achieving up to 98.1% attack success.

2605.10133May 11, 2026Yue Li, Xiao Li, Hao Wu +5

When Are LLM Inferences Acceptable? User Reactions and Control Preferences for Inferred Personal Information

Users are more curious than distressed by LLM inferences about personal data, with acceptability depending on context and third-party use.

2605.10013May 11, 2026Kyzyl Monteiro, Minjung Park, Alexander Ioffrida +6
PreviousPage 3 of 26Next

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.