cs.CR · 2026-10-15 · No. 144
Cryptography and Security, 2026-10-15.
4 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
4 entries-
01
P2Patch: Exploit-Guided Vulnerability Repair
Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat, Ali Javidi Ghasr, Maxime Newman Nereyabagabo, Kousha Amouzesh,...
cs.CR · cs.AI · cs.SE
Large language models are increasingly deployed as autonomous agents for automated program repair, patching software vulnerabilities through multi-step reasoning and tool use. Yet these systems typically validate a patch against the same evidence used to construct it -- a static alert, sanitizer trace, published exploit, or test suite. A patch that blocks that one piece of evidence can therefore look successful while remaining vulnerable to...
-
02
CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection
Qichen Zhao, Shengfang Zhai, Qingni Shen, Zhonghai Wu, Jiaheng Zhang
cs.CR · cs.AI
Agents extend their capabilities through reusable skills that package instructions, executable code, and resources. Composing these skills enables complex task workflows, but their dependencies can also connect malicious operations across skills, making their combined intent difficult to identify through individual-package auditing. We introduce CoRedSkill, a compositional red-teaming method that forms stealthy attacks through cooperating...
-
03
Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness
Behrad Tajalli, Henk Berendsen, Xiaoyun Xu, Stjepan Picek
cs.CR · cs.AI
Backdoor attacks on deep neural networks are commonly evaluated by attack success rate and benign accuracy, yet their stealthiness remains inconsistently defined and measured. Existing work often studies only one observable aspect of stealthiness, such as trigger imperceptibility, feature-space separability, parameter-space concentration, or evasion of particular defenses. This creates a fragmented picture: an attack may appear stealthy under...
-
04
Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options?
Yuanbo Xie, Mingli Zhu, Tianyun Liu, Yingjie Zhang, Haixiao Xiong, Tingwen Liu
cs.CR · cs.AI
Typed decision models (TDMs) are increasingly used in applications such as request routing and model selection, making reliable decisions critical to system performance. Fallback options accommodate categories outside regular choices, enabling deferral to human experts or more capable models. While recent works have examined adversarial vulnerabilities in TDMs, their ability to follow fallback rules in non-adversarial settings remains...
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.