cs.CR · 2026-11-11 · No. 170
Cryptography and Security, 2026-11-11.
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
MammothDP: Private Boosted Decision Trees Ready for Trusted Hardware and Leakage-free Hyperparameters
Moritz Kirschte, Thorsten Peinemann, Kari Kostiainen, Jan Wichelmann, Thomas Eisenbarth, Esfandiar Mohammadi
cs.CR · cs.DB · cs.LG
Data spaces like the European Health Data Space (EHDS) require the protection of sensitive data in studies during the data's processing and the study's release alike. In this work, we investigate how to implement this mandate using established trusted execution environments (TEEs) and timing side-channel hardening to protect the processing even under a compromised server, and the state-of-the-art differential privacy (DP) notion to protect...
-
02
Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models
Tomer Solberg
cs.CR · cs.AI · cs.LG
We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the...
-
03
What a CAGE 4 Score Measures: An Audit of a Learned Cyber-Defense Benchmark, Its Reference Defenders, and the Tables Built on Them
James Rice, Ji Hwan Park, Andres Kwasinski
cs.CR · cs.LG
CAGE Challenge 4 is the benchmark on which learned multi-agent cyber defenders are compared. We reproduce its two reference defenders, KEEP and H-MARL Expert, in a pinned container and show that three things read from it measure less than they are taken to measure. First, the simulator silently discards any action asserted for an agent whose previous action is still running, and charges one point for a discarded Restore as for one that runs....
-
04
Gradient Inversion through Linear and Affine Subspace Constraints
Konstantinos Bouros, Athanasios P. Liavas
cs.CR · cs.LG
Federated learning enables multiple clients to collaboratively train a machine-learning model without directly sharing their local datasets. However, as prior works have shown, the gradients exchanged during training may reveal sensitive information about client data. Most existing attacks usually optimize dummy inputs to match the true client gradients (Gradient Inversion Attacks), while some attempt to reconstruct them based on the...
-
05
From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses
Simon Hegelich, Bardh Prenkaj, Habiba Sarhan, Morteza Shahrezaye, Kolja Hegelich, Christian Montag, Ralf Schneider,...
cs.CR · cs.AI
AI coding harnesses couple language models to shells, filesystems, and network sockets, turning the harness into an automated Living-off-the-Land (LotL) platform: once an adversary injects instructions into retrieved content, dual-use binaries such as bash, curl, and find become the payload. We argue that security in agentic systems is a structural property of the cognitive architecture and permission composition rather than an emergent...
-
06
Domain-Invariant and Language-Model-Assisted Acoustic Side-Channel Attacks on Keyboards
Bikrant Bikram Pratap Maurya
cs.CR · cs.AI
Acoustic side-channel attacks (ASCA) recover typed text from the sound of keystrokes, using only a commodity microphone and no access to the victim's device. Prior work establishes that such attacks succeed under idealized laboratory conditions - a single keyboard, a fixed microphone, a quiet room, and training and testing on the same device but leaves open the question that matters for security: whether keystroke inference survives the open...
-
07
On Private Knowledge Retrieval and Private Inference for secure multi-agent systems
Vicenç Torra, Maria Bras-Amorós
cs.CR · cs.AI
Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an autonomous way. Agentic AI is the new term to denote these AI-based autonomous systems. In real multi-agent systems, agents need to deal with malicious agents some of which can exploit security vulnerabilities to do...
-
08
MOAI: Module-Optimizing Architecture for non-interactive secure transformer Inference
Linru Zhang, Xiangning Wang, Jun Jie Sim, Zhicong Huang, Jiahao Zhong, Huaxiong Wang, Pu Duan, Kwok-Yan Lam
cs.CR · cs.AI
Privacy concerns have been raised in Large Language Models (LLM) inference when models are deployed in Cloud Service Providers (CSP). Homomorphic encryption (HE) offers a promising solution by enabling secure inference directly over encrypted inputs. However, the high computational overhead of HE remains a major bottleneck. To address this challenge, we propose MOAI, an efficient HE-based, non-interactive framework for secure transformer...
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.