cs.CR · 2026-05-22 · No. 7
Cryptography and Security, 2026-05-22.
9 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
9 entries-
01
Innovations in Cardless Artificial Intelligence Banking: A Comprehensive Framework for Cyber Secure and Fraud Mitigation using Machine Learning Algorithms
Md Israfeel
cs.CR · cs.AI · cs.LG · cs.SE
The advent of cardless artificial intelligence (AI) banking heralds a paradigm shift in the financial landscape, offering users unprecedented security and convenience. This paper outlines a comprehensive framework designed to enhance cybersecurity, introduce auto-generated virtual cards, and mitigate fraud risks within cardless AI banking systems. The framework envisions a future banking architecture that employs AI-powered data cryptography...
-
02
Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
Sahar Abdelnabi, Chris Hicks, Konrad Rieck, Ahmad-Reza Sadeghi
cs.CR · cs.AI
The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.
-
03
A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers
Andrii Tyvodar, Andreas Rechberger, Dirmanto Jap, Shivam Bhasin, Bernhard Jungk, Jakub Breier, Xiaolu Hou
cs.CR · cs.AI
Embedded neural-network inference can leak information through timing side channels, including leakage caused by the evaluation of activation functions. This work proposes a constant-time implementation methodology for activation functions on embedded microcontrollers and validates it on ReLU, sigmoid, tanh, GELU, and Swish on an ARM Cortex-M4 platform. The proposed methodology combines branchless selection, fixed-cost Padé-based...
-
04
Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection
Štefan Kučerák, Jakub Breier, Xiaolu Hou
cs.CR · cs.AI · cs.LG
Vision processing units and other commercial neural-network inference accelerators are increasingly deployed in safety-relevant edge applications, but their fault response under transient hardware disturbances remains poorly characterized in the open literature. For the Intel Movidius Myriad X, packaged as the Intel Neural Compute Stick 2 (NCS2), only a single feasibility study has been published. We report a systematic single-pulse...
-
05
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
Quang Duc Nguyen, Siyuan Liang, Yiming Li, Fushuo Huo, Dacheng Tao
cs.CR · cs.AI · cs.LG
Time Series Forecasting (TSF) plays a critical role across many domains, yet it is vulnerable to backdoor attacks. However, backdoor defenses tailored to TSF remain underexplored, due to data entanglement and task-formulation shift challenges. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure modes. Our results reveal two fundamental issues:...
-
06
Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
Jianan Ma, Xiaohu Du, Ruixiao Lin, Yaoxiang Bian, Jialuo Chen, Jingyi Wang, Xiaofang Yang, Shiwen Cui, Changhua...
cs.CR · cs.AI · cs.SE
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn, stateless behaviors, overlooking the expanded attack surface inherent in stateful, multi-turn interactions and dynamic tool invocations. In this paper, we propose a novel, multi-dimensional evasion framework...
-
07
Adversarial Trust Poisoning in Vehicular Collaborative Perception
Yutong Liu, Chenyi Wang, Ming F. Li, Qingzhao Zhang
cs.CR · cs.AI
Collaborative perception (CP) enables connected and autonomous vehicles to share sensor data and jointly reason about their environment. To defend against adversaries that fabricate or manipulate shared data, existing systems employ cross-vehicle inconsistency detection and trust estimation, penalizing vehicles whose observations conflict with the majority. In this work, we show that these defenses themselves introduce a new attack surface....
-
08
Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
Yilan Gao, Sida Huang, Hongyuan Zhang, Xuelong Li
cs.CR · cs.AI
Closed-weight generative services are increasingly deployed through query-based APIs, where users can obtain generated outputs while model parameters remain inaccessible. However, such deployment does not prevent model stealing: an attacker can repeatedly query the service, collect large volumes of released synthetic images, and use them as training data for a private substitute model. This query-output-driven process enables unauthorized...
-
09
Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems
Aaditya Pai
cs.CR · cs.AI · cs.CL
Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, what we call domain camouflaged injection, standard detectors fail to flag them, with detection rates dropping from 93.8% to 9.7% on Llama 3.1 8B and...
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.