Cryptographic Implementations and Security

Latest papers

• Curvature Cryptanalysis of Smooth Transformer Feed-Forward Networks

  Munawar Hasan, Apostol Vassilev · 18 September 2026

  We show that smooth two-layer feed-forward networks (FFNs) expose an additional structural model extraction channel under a chosen-input raw-output oracle at the FFN branch; consider transformer FFN branches with GELU or SiLU activations under chosen-input raw-output access, without access to parame…

• Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers

  Ligong Han, Kai Xu, Hao Wang, Ruijiang Gao, Akash Srivastava · 7 July 2026

  Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlinear blocks. We study whether Structured Newton Layer Parallelism (SNLP) can make this inter-layer composition more FHE-f…

• Deep Learning-Assisted Improved Differential Fault Attacks on Lightweight Stream Ciphers

  Kok Ping Lim, Dongyang Jia, Iftekhar Salam · 20 May 2026

  Lightweight cryptographic primitives are widely deployed in resource-constrained environments, particularly in Internet of Things (IoT) devices. Due to their public accessibility, these devices are vulnerable to physical attacks, especially fault attacks. Recently, deep learning-based cryptanalytic …

• Property-Preserving Hashing for $\ell_1$-Distance Predicates: Applications to Countering Adversarial Input Attacks

  Hassan Asghar, Chenhan Zhang, Dali Kaafar · 14 April 2026

  Perceptual hashing is used to detect whether an input image is similar to a reference image with a variety of security applications. Recently, they have been shown to succumb to adversarial input attacks which make small imperceptible changes to the input image yet the hashing algorithm does not det…

• Efficient Parallel Algorithm for Decomposing Hard CircuitSAT Instances

  Victor Kondratiev, Irina Gribanova, Alexander Semenov · 20 February 2026

  We propose a novel parallel algorithm for decomposing hard CircuitSAT instances. The technique employs specialized constraints to partition an original SAT instance into a family of weakened formulas. Our approach is implemented as a parameterized parallel algorithm, where adjusting the parameters a…

• The Weight of a Bit: EMFI Sensitivity Analysis of Embedded Deep Learning Models

  Jakub Breier, \v{S}tefan Ku\v{c}er\'ak, Xiaolu Hou · 19 February 2026

  Fault injection attacks on embedded neural network models have been shown as a potent threat. Numerous works studied resilience of models from various points of view. As of now, there is no comprehensive study that would evaluate the influence of number representations used for model parameters agai…

• The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses

  Grzegorz G{\l}uch, Berkant Turan, Sai Ganesh Nagarajan, Sebastian Pokutta · 22 January 2026

  We formalize and analyze the trade-off between backdoor-based watermarks and adversarial defenses, framing it as an interactive protocol between a verifier and a prover. While previous works have primarily focused on this trade-off, our analysis extends it by identifying transferable attacks as a th…

• Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Dataset

  Vladimir Frants, Sos Agaian · 9 January 2026

  Adverse-weather image restoration (e.g., rain, snow, haze) models remain highly vulnerable to gradient-based white-box adversarial attacks, wherein minimal loss-aligned perturbations cause substantial degradation in the restored output. This paper presents QHNet, a computationally efficient purifica…

• Scaling Laws for Black box Adversarial Attacks

  Chuan Liu, Huanran Chen, Yichi Zhang, Jun Zhu, Yinpeng Dong · 19 December 2025

  Adversarial examples exhibit cross-model transferability, enabling threatening black-box attacks on commercial models. Model ensembling, which attacks multiple surrogate models, is a known strategy to improve this transferability. However, prior studies typically use small, fixed ensembles, which le…