Cryptography and Security

Papers filed under cs.CR on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

2,521 to 2,547 of 2,547

Explainability Boosted Anomaly Detection Framework for O-RAN based NextG Networks
Nurullah Aksu, Ali Fuat Sahin, Semiha Tedik Başaran
eess.SPcs.CRcs.LGarXiv:2608.14826v12026
Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
Barkha Rani
cs.CRarXiv:2607.06815v12026
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
Pedro Conde, Henrique Branquinho, Valerio Mazzone +3
cs.AIcs.CRarXiv:2605.10834v32026
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
Paul Kassianik, Blaine Nelson, Yaron Singer
cs.CRcs.AIarXiv:2607.15263v32026
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
Yong Yang, Xing Zheng, Huiyu Wu +7
cs.CRarXiv:2606.31227v12026
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
Yimeng Chen, Nathanaël Denis, Roberto Di Pietro +1
cs.CRcs.AIcs.CLarXiv:2607.17986v12026
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
Lehan Wang, Boli Chen, Ruixue Ding +7
cs.CRcs.AIcs.CLarXiv:2607.26791v12026
Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion
Cédric Bonhomme, Alexandre Dulaunoy
cs.CRarXiv:2607.25572v12026
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
Pingyu Wu, Lingyao Zhu, Weiming Zhang +1
cs.CRcs.AIarXiv:2607.27951v12026
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents
Ads Dawson, Adrian Wood
cs.CRcs.AIarXiv:2607.26314v12026
GPT-Red: Automated Red Teaming via Self-Play at Scale
Eric Wallace, Christopher A. Choquette-Choo, Nikhil Kandpal +15
cs.CRcs.AIcs.CLarXiv:2607.26115v12026
CipherSight: Robust Website Fingerprinting via Record-Resource Semantic Supervision under Distribution Shifts
Runhan Song, Qiqi Liu, Chuanzhou Pan +6
cs.CRcs.AIcs.NIarXiv:2608.13905v12026
Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models
Hongxin Xu, Jianping Mei, Can Wang +1
eess.IVcs.AIcs.CRarXiv:2608.13597v12026
What AI Red-Team Evaluations Can and Cannot Prove
Bandana Kaur
cs.AIcs.CRarXiv:2607.21735v22026
Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis
Aryan Luthra, Kshitij Jain, Siddharth Arya +2
cs.AIcs.CRcs.LGarXiv:2608.13608v12026
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Jiaming Zhang, Boyang Chen, Zherui Li +14
cs.CRcs.CVarXiv:2608.04314v12026
P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
Myunghoon Ryu, Geunpyo Park, Sungjoon Lee +2
cs.CRcs.AIarXiv:2608.14094v12026
QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation
Lin-Fa Lee, Yi-Yu Chang, Kuo-Hei Yeh
cs.AIcs.CRarXiv:2608.14149v12026
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
Mingxuan Zhang, Jiahui Han, Dadi Guo +5
cs.CRcs.AIarXiv:2606.00152v22026
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
Zonghao Ying, Xiangfan Wu, Huiyu Wu +4
cs.CRarXiv:2608.03509v22026
A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation
Dipankar Sarkar
cs.CRcs.AIcs.CLarXiv:2608.14329v12026
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
Yanting Wang, Chenlong Yin, Runpeng Geng +1
cs.CRarXiv:2608.05108v12026
A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Process Models
Md Kamrul Islam, Tiphaine Henry, Mattia Salnitri +2
cs.CRcs.AIcs.SEarXiv:2608.14370v12026
BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows
Sheng Hong, Yixuan Huang, Weiwei Jiang +3
cs.CRcs.AIarXiv:2608.14126v12026
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Thiago Sandoval, Ufuk Topcu
cs.AIcs.CLcs.CRarXiv:2608.14089v12026
Agent Safety Should Be a Runtime Contract
Albus W. Ng, Yi Han, Jusheng Zhang +1
cs.CRcs.AIarXiv:2608.11274v12026
Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks
MD Azizul Hakim, Md Shihab Uddin, Talha Ibne Anis
cs.CRcs.AIarXiv:2607.00553v12026

Cryptography and Security

Explainability Boosted Anomaly Detection Framework for O-RAN based NextG Networks

Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies

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

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming

Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response

Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion

Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

GPT-Red: Automated Red Teaming via Self-Play at Scale

CipherSight: Robust Website Fingerprinting via Record-Resource Semantic Supervision under Distribution Shifts

Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models

What AI Red-Team Evaluations Can and Cannot Prove

Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis

Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle

P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems

QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation

Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Process Models

BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows

Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers

Agent Safety Should Be a Runtime Contract

Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks