cs.CR · 2026-09-05 · No. 106
Cryptography and Security, 2026-09-05.
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
SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center
Uday Vallabhaneni, Cassie L. Cagwin, David J. Wild
cs.CR · cs.AI
Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale: a finite context window cannot hold a multi-thousand-host authentication graph, and free-form generation offers no guarantee that a recommended containment action is consistent with the topology it operates on. We present Sentinel-RL, an agentic-SOC architecture that decouples topological...
-
02
A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequences for Security and AI
Fabio F. G. Buono
cs.CR · cs.AI · cs.LO
For every coherent and sufficiently expressive finite syntactic system S, we prove the existence of at least one theorem that S cannot produce autonomously. The result is a metatheorem: it proves the existence of a theorem, and applies to every finite syntactic system - security mechanisms, AI systems, formal verifiers, legal systems, economic models, and the formal system in which it is itself proved.
-
03
PatchBench: Evaluating AI Agents for Vulnerability Patching
Chihao Shen, Jiacheng Li, Aastha Mahajan, Jeffery Siyuan Tian, Yonghwi Kwon, Yizheng Chen
cs.CR · cs.AI · cs.SE
AI agents have recently demonstrated strong performance in automated vulnerability patching. However, existing evaluations often validate a patch only by testing whether the provided Proof-of-Concept (PoC) input still triggers a crash. This leaves two key threats to validity: agents may reproduce memorized historical developer patches, or they may generate surface-level fixes that only suppress the reported crash. We study these concerns for...
-
04
A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors
Pengxun Li, Litian Zhang, Jianwei Hou, Shujiang Wu, Song Li, Zifeng Kang, Xi Zhang
cs.CR · cs.AI
Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These commands run with host privileges yet ship as lifecycle-hook configuration and may fire at times the LLM never observes. We identify the lifecycle-hook update path, which harnesses trust blindly, as a new attack surface. Under a supply-chain threat model in which an attacker controls only plugin...
-
05
Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference
Simone Ceppi, Ignacio Sanchez
cs.CR · cs.CL · cs.LG
We introduce Stateless Bernoulli Watermarking (SBW), a new statistical watermark for Large Language Models that determines green list membership through independent per-token Bernoulli trials. Unlike KGW's vocabulary permutation or SynthID's multi-layer tournament, SBW requires only a single comparison per token against a counter-based random number generator, reducing membership complexity to $O(1)$ and enabling single-kernel execution with...
-
06
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface
Adrita Rahman Tory, ABM Shawkat Ali, Md Abu Layek, Khondokar Fida Hasan
cs.CR · cs.AI · cs.LG
Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deployment in operational environments must simultaneously satisfy three competing requirements: formal differential privacy guaranties, tolerance to Byzantine-adversarial participants, and reliable detection coverage across severely imbalanced attack categories. Existing literature treats these...
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.