cs.CR · 2026-08-13 · No. 83
Cryptography and Security, 2026-08-13.
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
Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
Junliang Liu, Ruoyu Li, Wenxin Tang, Jingyu Xiao, Zhenyu Liu, Jingheng Xu, Laizhong Cui
cs.CR · cs.AI
LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly trajectory. Prior work studies selection manipulation, malicious skill instructions, and tool-chain resource amplification...
-
02
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
Jin Lu, Xuening Han, Yang Zhong, Lin Tan, Kevin Luo, Andrew Gacek, Neha Rungta
cs.CR · cs.AI · cs.CL · cs.SE
Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VICs) - the commits that first introduce vulnerabilities into codebases. VICs are essential for determining the full range of vulnerable software versions. Existing vulnerability datasets suffer from limited programming language coverage, restricted patch complexity, and narrow project scope. Through our dual annotation by human...
-
03
Machine Learning-Based Cyber Defense for Cloud Infrastructure: An Adaptive Deep Q-Network Architecture for Intelligent Intrusion Detection and Automated Threat Mitigation
Md Yassir Mottalib, Md Yousuf, Eklachur Rahman Bhuiyan, S M Ahsan Habib, Sonjoy Kumar Dey, Md. Salahuddin Gazi,...
cs.CR · cs.AI
With the increasing complexity of cyber assaults in cloud environments, adaptable security solutions are needed that can support real-time detection and autonomous response. In this paper, we propose a reinforcement learning-based dynamic cyber defense framework. We deploy a Deep Q-Network (DQN) to train effective defensive strategies to counteract the evolving cyberattacks. We leverage the CICIDS2017 dataset for model creation and the...
-
04
How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment
Guang Yang, Fengchen Liu, Alex Wang, Homa Hosseinmardi, Amir Ghasemian
cs.CR · cs.AI · cs.CL
State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been systematically examined. We construct a balanced benchmark of 200 core entries spanning ten politically sensitive topics, plus a seven-variant visual-abstraction probe, and run nine vision-language models (VLMs), seven China-origin and two non-China, across four...
-
05
Towards Model-based Run-time Cybersecurity: On Control-Flow Anomaly Detection, Attack Identification, and Hardware Monitoring
Martin Sachenbacher, Martin Leucker, Alexander Weiss, Aliyu Tanko Ali
cs.CR · cs.AI
Methods to increase the resilience of systems to cyber-attacks become increasingly important. Control-flow monitoring provides a principled basis to ensure integrity and detect possible anomalies at run-time. Once anomalies have been detected, so-called attack trees can be used to identify possible types of attacks. However, this approach is vulnerable to camouflage, by which attackers try to evade detection (and correct identification) by...
-
06
Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation
Yuanmin Huang, Chen Chen, Geng Hong, Xiaoyu You, Hui Xue, Zhenxing Qian, Mi Zhang, Min Yang
cs.CR · cs.AI
Proprietary text-to-image diffusion models are increasingly distributed as hosted services and downloadable checkpoints, making their intellectual property (IP) protection an increasingly critical concern when model leakage, copying, or unauthorized fine-tuning is disputed. In this work, we present a non-invasive model fingerprinting framework based on \emph{collapsed generation}, a phenomenon where certain input conditions produce highly...
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.