cs.CR · 2026-07-08 · No. 47
Cryptography and Security, 2026-07-08.
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
Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles
Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano, Joaquin Garcia-Alfaro
cs.CR · cs.CV · cs.LG
Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used for training and (ii) embedding of backdoors that may eventually be triggered later on, when specific conditions in the system apply over the learned models. Its impact over data augmentation models is unclear. While data augmentation reduces the likelihood of poisoning attack success, some valid...
-
02
Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy
Nikita P. Kalinin, Rasmus Pagh
cs.CR · cs.LG
We present the dithered Gaussian mechanism, a novel alternative to the discrete Gaussian mechanism for differential privacy that discretizes the private output rather than the noise distribution itself. By interpreting this discretization as post-processing of the Gaussian mechanism, our construction directly inherits the privacy guarantees of the standard Gaussian mechanism while avoiding vulnerabilities caused by finite-precision...
-
03
REAN: Reconstruction-aware ECG Anonymization Based on Privacy--Utility Orthogonality
Taerin Ki, Sunghwan Park, Junyoung Park, Jaewoo Lee
cs.CR · cs.LG
A shared electrocardiogram (ECG) is itself a biometric fingerprint that can re-identify a patient and reveal personal information. Recent ECG anonymizers transform the signal before sharing to reduce privacy leakage. However, existing methods still face a privacy--utility trade-off, in which preserving privacy often compromises utility while preserving utility reveals personal information. We propose \emph{REAN} (\emph{RE}construction-aware...
-
04
Multi-Channel Spread-Spectrum Code Watermarking
Soohyeon Choi, Debin Gao, Yue Duan
cs.CR · cs.LG · cs.SE
Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need. Generation-time schemes require access to the producing model and cannot be applied to third-party code, while post-hoc schemes work on any code but carry at most 4 bits of payload, far too few to distinguish the many deployed model configurations. We present multi-channel...
-
05
Bit2Watt: A Cyber-Physical Vulnerability Exploiting GPU Workloads Across Power and Computing Infrastructures
Zhouhao Ji, Kaikai Pan, Wenyuan Xu
cs.CR · cs.AR · cs.DC
Modern data centers increasingly rely on large-scale GPU clusters and on-site renewable energy resources, resulting in a tightly coupled cyber-physical system between computing workloads and power-electronic-dominated grids. In this paper, we reveal Bit2Watt, a previously unexplored vulnerability in which an adversary manipulates GPU workloads to induce controlled, high-frequency power modulations that destabilize local power infrastructure...
-
06
i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler
Rakesh Podder, Wadia Ganim, Sarath Sreedharan, Indrajit Ray, Indrakshi Ray
cs.CR · cs.AI
i-EXAM is a planning-powered tool that helps system administrators to create security profiles of complex networks and perform what-if analyses to identify network hardening strategies. It leverages planning compilation that provides soundness and completeness guarantees to identify attack paths, evaluate security metrics, generate diverse hardening strategies, and explain these strategies in natural language using Large Language Models.
-
07
Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations
Mohammadreza Rashidi
cs.CR · cs.AI · cs.SE
The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools. A server advertises each tool through a tools/list handshake that returns a name, a natural-language description, and a JSON input schema. The client renders this metadata once, in a one-time approval dialog, and then injects it verbatim into the model's context on every subsequent turn. Nothing in the protocol requires the rendered approval...
-
08
The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities
Mohammadreza Rashidi
cs.CR · cs.AI
AI coding agents now read repositories, call tools, and execute shell commands with limited human oversight, and a fast-growing body of work studies whether the execution layer around them is actually safe. That literature is scattered. Papers on sandbox isolation, capability and access control, policy enforcement, time-of-check-to-time-of-use (TOCTOU) races, Model Context Protocol (MCP) threats, identity delegation, execution provenance,...
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.