cs.CR · 2026-07-28 · No. 67
Cryptography and Security, 2026-07-28.
6 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
6 entries-
01
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Arseny Kravchenko, Vadim Liventsev, Innokentii Konstantinov, Ildar Iskhakov, Matvey Kukuy
cs.CR · cs.AI
Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (IFC) provides structural security guarantees, traditional taint tracking permanently taints an agent's context upon reading unvetted data, severely restricting downstream utility. We present APPA (Agentic Permissions Policy Algebra), an IFC framework that resolves...
-
02
When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs
Tong Zhang, Zexin Li, Simin Chen, Yun Peng
cs.CR · cs.LG
Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cost. Rather than treating defenses as a single class, we organize them by operational strategy and examine how different strategies correlate with...
-
03
DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense
Trung V. Phan, Tri Gia Nguyen, Thomas Bauschert
cs.CR · cs.AI
Advanced Persistent Threats (APTs) are difficult to detect and interpret due to their multi-stage and stealthy nature. While recent autonomous defense systems leverage provenance graphs and learning-based models for detection and mitigation, their outputs remain largely machine-oriented and difficult for analysts to interpret. Large language models (LLMs) offer a promising interface for report generation, but often produce hallucinated or...
-
04
EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability
Andrea Ponte, Daniel Gibert, Matous Kozak, Dmitrijs Trizna, Maura Pintor, Battista Biggio, Fabio Roli, Luca Demetrio
cs.CR · cs.LG
Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their brittleness against...
-
05
Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation
Mohan Manivannan, Dalal Alharthi
cs.CR · cs.AI · cs.DC
Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident reconstructing context the logs already contain. We present Cloud Decoy AI Agent, a framework pairing a high fidelity cloud decoy with an autonomous language...
-
06
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation
Susil Kumar Mohanty, Rohit Patel, Kosuru Yuvaraj, Jeenal Chaudhary, Disha Singhania
cs.CR · cs.AI · cs.CL · cs.LG
Retrieval-Augmented Generation (RAG) lets a large language model answer questions using documents retrieved from an external knowledge base at query time. This makes RAG useful for private data, fast-changing information, and reducing hallucination, but it also means the model's answer is only as trustworthy as whatever the retriever hands it. If the knowledge base accepts writes from more than one party, an attacker needs only a handful of...
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.