cs.CR · 2026-06-15 · No. 24
Cryptography and Security, 2026-06-15.
8 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks
Jianzhe Lin
cs.CR · cs.AI
Verifier-driven self-DPO is a common recipe for self-improving production visual-language models. In this setup, a frozen verifier scores candidate generations, the top- and bottom-scoring candidates form a preference example, and DPO updates the learner. The deployment-time assumption is monotone: a stronger verifier should yield a stronger student. We show that this assumption can fail because verifier quality is highly task-specific. On a...
-
02
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
Yuguang Zhou, Xunguang Wang, Pingchuan Ma, Zhantong Xue, Zhaoyu Wang, Shuai Wang
cs.CR · cs.AI
LLM-based guardrails have emerged as a highly effective defense against prompt injection and jailbreak attacks in autonomous agents. However, we reveal that the very reasoning and task-following capabilities enabling this protection introduce a novel vulnerability: attackers can inject crafted data to trap the guardrail in extended reasoning loops, effectuating a systematic denial-of-service (DoS) attack. To systematically expose this threat,...
-
03
Securing the Future of IoMT in the Post-Quantum Era: An Edge-Native Federated Learning Approach
Taym Alshoghri, Deemah H. Tashman, Mohammad Reza Gerami, Soumaya Cherkaoui
cs.CR · cs.AI
Internet of Medical Things (IoMT) devices operate under strict resource constraints while handling highly sensitive health data, making security and privacy critical concerns. Federated learning (FL) further complicates this landscape, as model updates exchanged during training may unintentionally expose private medical information. Emerging quantum computing capabilities threaten the long-term viability of conventional lightweight...
-
04
AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges
Fengyu Liu, Jiarun Dai, Yihe Fan, Wuyuao Mai, Ziao Li, Bofei Chen, Jie Zhang, Zheng Lou, Bocheng Xiang, Qiyi Zhang,...
cs.CR · cs.AI · cs.LG
Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation. However, evaluating their offensive capabilities remains constrained by limited access to open, reproducible, multi-host cyber ranges. Existing public benchmarks capture isolated skills such as CTF solving, vulnerability reproduction, and exploit generation, but often abstract away realistic intrusion...
-
05
From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models
Zixuan Gu, Xiaojun Ye, Yang Liu
cs.CR · cs.AI
Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment. Split learning has therefore emerged as a promising paradigm for LLM fine-tuning and inference under limited local resources. However, it introduces new privacy risks. Prior work primarily studies leakage of private input prompts,...
-
06
Same-Origin Policy for Agentic Browsers
Xilong Wang, Xiaoxing Chen, Patrick Li, Dawn Song, Neil Gong
cs.CR · cs.AI · cs.CL · eess.SY
Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instructions. The same-origin policy (SOP) is a fundamental browser security mechanism that prevents unauthorized automated cross-origin data flows induced by scripts. However, whether SOP remains effective in agentic browsers is an open question that has not been systematically studied. In this work, we bridge...
-
07
Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH
Vikhyath Kothamasu, Virginia Smith, Chhavi Yadav
cs.CR · cs.AI · cs.LG
LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world. A key emerging threat is Decomposition Attacks \cite{glukhov2024breach, jones2024adversaries} in which a harmful task is broken into simpler, benign subtasks that evade safety mechanisms when executed separately but cumulatively fulfill the malicious intent. Although recent benchmarks assess agent...
-
08
Side-Channel Attacks Bypass Protection in 3D Printers
Eric Yocam, Varghese Vaidyan, Micah Flack, Gurcan Comert, Judith L. Mwakalonge
cs.CR · cs.ET · cs.LG
Active Motor Noise Cancellation (AMNC) ships in commercial fused deposition modeling (FDM) 3D printers as a hardware countermeasure against acoustic side-channel attacks that target intellectual property (IP). We present the first empirical evaluation of a deployed AMNC countermeasure, using a public dataset of synchronized acoustic and vibration recordings from two AMNC-equipped Bambu Lab printers across 12 object classes. AMNC fully...
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.