cs.CR · 2026-06-28 · No. 37
Cryptography and Security, 2026-06-28.
11 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
11 entries-
01
Tilikum: Transaction Fair Ordering on a DAG without Weak Edges
Giulio Segalini, Yigit Çolakoğlu, Marko Putnik, Jérémie Decouchant
cs.CR · cs.DC
Decentralized Finance (DeFi) applications rely heavily on the order in which transactions are executed, making them susceptible to reordering attacks that enable adversaries to extract Blockchain Extractable Value (BEV). While linear blockchain systems such as Ethereum have inspired extensive research into fair ordering mechanisms, DAG-based consensus protocols have remained largely unprotected despite their growing adoption for scalability...
-
02
Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions
Gerhard Backfried, Christian Schmidt, Diego Pilutti, Michael Suker
cs.CR · cs.AI
We present a novel approach for applying Large Language Models (LLMs) to threat assessment in the context of foreign peacekeeping missions. Building on the PINPOINT project and its use case, the EU Monitoring Mission in Georgia, we combine an interdisciplinary risk-model with OSINT-based media collection and LLM-supported threat extraction. The proposed workflow maps media contents to mission-relevant threats, extracts structured information...
-
03
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
Ryan Fetterman
cs.CR · cs.AI
LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data. We show that this can miss vulnerabilities introduced by fine-tuning itself: models can learn token-level indicator semantics that preserve canonical accuracy while failing under behavior-preserving transformations such as PowerShell alias substitution, command reconstruction, string construction, execution...
-
04
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
Liwei Liu, Tianzhu Han, Zijian Liu, Zishu Dong, Na Ruan
cs.CR · cs.AI
With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP has also introduced novel security concerns such as Tool Poisoning Attack (TPA), which exploit LLM-server interactions to inject malicious prompts. Existing poisoning schemes typically adopt a monolithic plaintext...
-
05
Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries
Prarabdh Shukla, Ritik, Suhas Rao, Arpit Agarwal, Arjun Bhagoji
cs.CR · cs.CL · cs.LG
With a profusion of jailbreaks for LLMs now widely known, a growing concern is that non-expert malicious actors ("the average Jane") could elicit actionable responses to malicious requests. In this work, we examine whether this concern is justified. A non-expert malicious actor requires two ingredients for a successful attack: a powerful jailbreak for their target model, acting on an effective malicious query. For the former, we propose a...
-
06
Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities
Corban Villa, Sohee Kim, Austin Chu, Alon Shakevsky, Raluca Ada Popa
cs.CR · cs.AI
AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms memory violations and efficiently filters false positives. Many dangerous vulnerability classes, such as cryptographic misuse, however, lack any comparable instrumentation. In this work, we present Chai, an AI-based system that discovers and validates cryptographic misuse vulnerabilities through naturally occurring...
-
07
Fortress and Gatekeeper: Theorizing Transitive Trust in Third-Party Cybersecurity Risk Governance
Yijun Chen, Misita Anwar
cs.CR · cs.AI · cs.CY
Third-party vendors, such as analytics platforms, cloud services, identity providers, and software suppliers, are increasingly embedded in digital service delivery. While these arrangements enable scale and specialization, they also move customer data and security-relevant practices into environments that customers rarely see, select, or evaluate. This paper examines this problem through a document analysis of the November 2025...
-
08
MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG
Inderjeet Singh, Andrés Murillo, Motoyoshi Sekiya, Yuki Unno, Junichi Suga
cs.CR · cs.AI · cs.LG
Multimodal agentic retrieval-augmented generation (RAG) systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks, and orchestrator-level tool manipulation. Existing red-teaming approaches are typically surface-specific and often recycle known attack templates; on text-poisoning benchmarks we measure 73-84% exact duplication. We present MIRROR, a unified cross-surface framework...
-
09
DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors
Christian Scano, Diego Soi, Angelo Sotgiu, Luca Demetrio, Davide Maiorca, Giorgio Giacinto, Fabio Roli, Battista Biggio
cs.CR · cs.LG
Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors. In this work, we first show that, despite claims, existing problem-space attacks remain largely impractical. Most techniques leverage software transplantation to inject entire benign modules, introducing many side-effect features and often causing build-time failures. Fine-grained methods that inject only a narrow subset of...
-
10
TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
Ngoc Bao Anh Le, Thai T. Vu, John Le, Heath Cooper, Jun Shen
cs.CR · cs.AI
Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes and making them incompatible with dynamic, large-scale financial graphs. We propose TGHE (Template-based Graph Homomorphic Encryption), an ego-centric framework that resolves this by exploiting a template phenomenon: local computation trees in transaction graphs...
-
11
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
Nada Lahjouji, Ashwin Gerard Colaco
cs.CR · cs.AI
Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data, privacy becomes harder to enforce. An agent touches many data sources, runs multi-step workflows, keeps state across sessions, and acts with delegated permissions. Sensitive information can therefore leak not...
This edition is part of The Daily Abstract — cs.CR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.