cs.CR · 2026-10-08 · No. 137
Cryptography and Security, 2026-10-08.
3 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
3 entries-
01
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Hui Zhang, Yachao Yuan, Jiayun Wang, Yuanzhuo Li, Hongtao Wang, Yali Yuan
cs.CR · cs.AI
Fine-tuning-as-a-service enables users to adapt aligned large language models (LLMs) to specialized tasks, but malicious fine-tuning can erode refusal behavior while preserving task performance on legitimate inputs. We revisit recent layer-wise safety diagnostics and find that safety sensitivity is signed: scaling different layers can strengthen refusal, weaken it, or have little effect. Motivated by this observation, we propose SLDR, a...
-
02
Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
Georgios Koutidis, Nikolaos Kekatos, Tom Nianios, Alexios Lekidis
cs.CR · cs.AI · cs.CL
Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated alerts and too few analysts. Large Language Models (LLMs) are increasingly proposed as reasoning engines that triage alerts and, in autonomous deployments, issue commands that block IPs, kill processes, or quarantine files on production hosts. This coupling introduces a new risk: a single...
-
03
Defensive Sufficiency in a Stackelberg Model of AI Security
Subhabrata Majumdar, Rajlakshmi Chavan
cs.CR · cs.AI
Feedback from automated testing, human red teaming, and incident response can strengthen an AI system's defenses when discovered failures lead to effective repairs. We study when this feedback process provides sufficient protection and when investing in it is economically worthwhile. We begin by showing that an attack surface composed of finite number of inputs is defended with probability 1 if every unresolved attack has a persistent chance...
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.