arXiv cs.CR

Cryptography and Security daily digest.

52 past editions, oldest first by date. Atom feed → · all categories

01 — Past editions

most recent first

2026-07-19 Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents 3 papers · No. 58
2026-07-18 Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents 3 papers · No. 57
2026-07-17 Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents 3 papers · No. 56
2026-07-16 Rethinking Penetration Testing for AI-Enabled Systems: From Resource... 12 papers · No. 55
2026-07-15 Watermark Forensics for Generative Models: An Information-Theoretic Perspective 3 papers · No. 54
2026-07-14 When Local Monitors Miss Compositional Harm: Diagnosing Distributed... 6 papers · No. 53
2026-07-13 VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents 5 papers · No. 52
2026-07-12 TRACE: A Two-Channel Robust Attribution Watermark via Complementary... 9 papers · No. 51
2026-07-11 TRACE: A Two-Channel Robust Attribution Watermark via Complementary... 9 papers · No. 50
2026-07-10 TRACE: A Two-Channel Robust Attribution Watermark via Complementary... 9 papers · No. 49
2026-07-09 Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents 6 papers · No. 48
2026-07-08 Assessing the Operational Impact of Poisoning Attacks over Augmented 3D... 8 papers · No. 47
2026-07-07 Selective Disclosure Watermarking for Large Language Models 8 papers · No. 46
2026-07-06 Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring 2 papers · No. 45
2026-07-05 Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring 2 papers · No. 44
2026-07-04 Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring 2 papers · No. 43
2026-07-03 Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring 2 papers · No. 42
2026-07-02 All-out Attack: Optimal Block Withholding Under Pay-Per-Share Scheme 5 papers · No. 41
2026-07-01 A Lifecycle and Application-Stack Survey of Large Language Model... 5 papers · No. 40
2026-06-30 MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems 7 papers · No. 39
2026-06-29 Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from... 6 papers · No. 38
2026-06-28 Tilikum: Transaction Fair Ordering on a DAG without Weak Edges 11 papers · No. 37
2026-06-27 Tilikum: Transaction Fair Ordering on a DAG without Weak Edges 11 papers · No. 36
2026-06-26 Tilikum: Transaction Fair Ordering on a DAG without Weak Edges 11 papers · No. 35
2026-06-25 Can Trustless Agents Be Trusted? An Empirical Study of the ERC-8004... 9 papers · No. 34
2026-06-24 Red-Teaming the Agentic Red-Team 3 papers · No. 33
2026-06-23 Detecting Malicious Agent Skills in the Wild using Attention 4 papers · No. 32
2026-06-22 Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in... 7 papers · No. 31
2026-06-21 Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in... 7 papers · No. 30
2026-06-20 Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in... 7 papers · No. 29
2026-06-19 Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in... 7 papers · No. 28
2026-06-18 OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition,... 6 papers · No. 27
2026-06-17 Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents 7 papers · No. 26
2026-06-16 Cross-Silo De-Anonymization Under Local Differential Privacy: Threat Model,... 4 papers · No. 25
2026-06-15 When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks 8 papers · No. 24
2026-06-14 Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for... 2 papers · No. 23
2026-06-13 Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for... 2 papers · No. 22
2026-06-12 Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for... 2 papers · No. 21
2026-06-11 Categorical Robustness Assessment for Machine Learning based Network... 6 papers · No. 20
2026-06-10 Do Transformers Actually Help Intrusion Detection? A Temporal Sequence... 10 papers · No. 19
2026-06-09 What the Eyes See, the LLMs Miss: Exploiting Human Perception for... 12 papers · No. 18
2026-06-08 From Privacy to Workflow Integrity: Communication-Graph Metadata in... 3 papers · No. 17
2026-06-07 Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band... 2 papers · No. 16
2026-06-06 Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band... 2 papers · No. 15
2026-06-05 Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band... 2 papers · No. 14
2026-06-02 Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools 3 papers · No. 13
2026-05-30 Token-Level Generalization in LoRA Adapter Backdoors: Attack... 10 papers · No. 12
2026-05-28 Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model... 4 papers · No. 11
2026-05-27 Risk Averse Alert Prioritization for IDS Using Subnormal Gaussian Fuzzy Models 5 papers · No. 10
2026-05-25 Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study... 6 papers · No. 9
2026-05-23 Innovations in Cardless Artificial Intelligence Banking: A Comprehensive... 9 papers · No. 8
2026-05-22 Innovations in Cardless Artificial Intelligence Banking: A Comprehensive... 9 papers · No. 7

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.