Evaluating PQC KEMs, Combiners, and Cascade Encryption via Adaptive IND-CPA Testing Using Deep Learning

• URL: http://arxiv.org/abs/2604.06942v1
• Date: Wed, 08 Apr 2026 11:06:05 GMT
• Title: Evaluating PQC KEMs, Combiners, and Cascade Encryption via Adaptive IND-CPA Testing Using Deep Learning
• Abstract summary: IND-CPA games as binary classification tasks and training on labeled ciphertext data with BCE loss are studied.<n>We specifically test the public-key encryption schemes used to construct examples such as ML-KEM, BIKE, and HQC.<n>In our experiments on PQC algorithms, KEM combiners, and cascade encryption, no algorithm or combination of algorithms demonstrates a significant advantage.
• Score: 5.464851570832092
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ensuring ciphertext indistinguishability is fundamental to cryptographic security, but empirically validating this property in real implementations and hybrid settings presents practical challenges. The transition to post-quantum cryptography (PQC), with its hybrid constructions combining classical and quantum-resistant primitives, makes empirical validation approaches increasingly valuable. By modeling IND-CPA games as binary classification tasks and training on labeled ciphertext data with BCE loss, we study deep neural network (DNN) distinguishers for ciphertext indistinguishability. We apply this methodology to PQC KEMs. We specifically test the public-key encryption (PKE) schemes used to construct examples such as ML-KEM, BIKE, and HQC. Moreover, a novel extension of this DNN modeling for empirical distinguishability testing of hybrid KEMs is presented. We implement and test this on combinations of PQC KEMs with plain RSA, RSA-OAEP, and plaintext. Finally, methodological generality is illustrated by applying the DNN IND-CPA classification framework to cascade symmetric encryption, where we test combinations of AES-CTR, AES-CBC, AES-ECB, ChaCha20, and DES-ECB. In our experiments on PQC algorithms, KEM combiners, and cascade encryption, no algorithm or combination of algorithms demonstrates a significant advantage (two-sided binomial test, significance level $α= 0.01$), consistent with theoretical guarantees that hybrids including at least one IND-CPA-secure component preserve indistinguishability, and with the absence of exploitable patterns under the considered DNN adversary model. These illustrate the potential of using deep learning as an adaptive, practical, and versatile empirical estimator for indistinguishability in more general IND-CPA settings, allowing data-driven validation of implementations and compositions and complementing the analytical security analysis.

Related papers

• Pseudonym Scheme Based on Hybrid Certificates for Security Credential Management System in Vehicular Communications [14.260839001419612]
  This study proposes a hybrid certificate that combines the Elliptic-Curve Cryptography (ECC) with Post-Quantum Cryptography (PQC)<n>This design aims to eliminate the possibility of inferring any correlation between the public key in a certificate and that in an enrollment certificate.
  arXiv  Detail & Related papers  (2026-06-12T00:59:42Z)
• Key Encapsulation Mechanism-Based Integrated Encryption Scheme (KEM-IES) [0.0]
  Elliptic Curve Integrated Encryption Scheme (ECIES) is widely regarded as a practical method.<n>The advancement of quantum computing technologies poses potential security risks to ECIES.<n>This study proposes a Key Encapsulation Mechanism-Based Integrated Encryption Scheme (KEM-IES)
  arXiv  Detail & Related papers  (2026-05-11T08:25:16Z)
• Statistical Channel Fingerprint Construction for Massive MIMO: A Unified Tensor Learning Framework [51.39651336043647]
  Channel fingerprint (CF) is considered a key enabler for facilitating the acquisition of channel state information inIMO communication systems.<n>We propose a novel type of CF that stores statistical CSI (sCSI) at each potential location, referred to as statistical CF (sCF)
  arXiv  Detail & Related papers  (2026-04-30T08:28:45Z)
• Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network [84.22115118596741]
  We propose an end-to-end deep learning (DL) framework with low inference complexity for symbol-level precoding.<n>We show that the proposed framework captures substantial performance gains of optimal SLP, while achieving an approximately 80-times speedup over conventional methods.
  arXiv  Detail & Related papers  (2025-10-02T15:15:50Z)
• Hybrid Schemes of NIST Post-Quantum Cryptography Standard Algorithms and Quantum Key Distribution for Key Exchange and Digital Signature [0.0]
  This study proposes hybrid schemes that integrate QKD with the National Institute of Standards and Technology (NIST) standardized PQC algorithms.<n>For the hybrid key exchange protocol, this study combines Module-Lattice-based Key Encapsulation Mechanisms (ML-KEM) with QKD protocols, specifically BB84 and E91.<n>In the design of the hybrid digital signature scheme, this study utilizes Module-Lattice-based Digital Signature Algorithms (ML-DSA) and Stateless Hash-based Digital Signature Algorithms (SLH-DSA) to generate signature reconstruction values.
  arXiv  Detail & Related papers  (2025-09-30T05:14:34Z)
• Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders [50.52694757593443]
  Existing SAE training algorithms often lack rigorous mathematical guarantees and suffer from practical limitations.<n>We first propose a novel statistical framework for the feature recovery problem, which includes a new notion of feature identifiability.<n>We introduce a new SAE training algorithm based on bias adaptation'', a technique that adaptively adjusts neural network bias parameters to ensure appropriate activation sparsity.
  arXiv  Detail & Related papers  (2025-06-16T20:58:05Z)
• Complexity of Post-Quantum Cryptography in Embedded Systems and Its Optimization Strategies [2.821324092673655]
  The National Institute of Standards and Technology (NIST) has initiated a standardization process for post-quantum cryptography (PQC) algorithms.<n>This paper first provides a comprehensive analysis of the hardware complexity of post-quantum cryptography (PQC) in embedded systems.<n>To address these challenges, this paper discusses optimization strategies such as pipelining, parallelization, and high-level synthesis.
  arXiv  Detail & Related papers  (2025-04-18T08:02:13Z)
• Cryptanalysis via Machine Learning Based Information Theoretic Metrics [58.96805474751668]
  We propose two novel applications of machine learning (ML) algorithms to perform cryptanalysis on any cryptosystem.<n>These algorithms can be readily applied in an audit setting to evaluate the robustness of a cryptosystem.<n>We show that our classification model correctly identifies the encryption schemes that are not IND-CPA secure, such as DES, RSA, and AES ECB, with high accuracy.
  arXiv  Detail & Related papers  (2025-01-25T04:53:36Z)
• Performance of Cascade and LDPC-codes for Information Reconciliation on Industrial Quantum Key Distribution Systems [69.47813697920358]
  We analyze, simulate, optimize, and compare the performance of two prevalent algorithms used for Information Reconciliation. We focus on their applicability in practical and industrial settings, operating in realistic and application-close conditions.
  arXiv  Detail & Related papers  (2024-08-28T12:51:03Z)
• CCA-Secure Hybrid Encryption in Correlated Randomness Model and KEM Combiners [3.837357895668154]
  A hybrid encryption (HE) system is an efficient public key encryption system for arbitrarily long messages. The HE encryption algorithm uses a KEM generated key k to encapsulate the message using DEM. The KEM/DEM composition theorem proves that if KEM and DEM satisfy well-defined security notions, then HE will be secure with well defined security.
  arXiv  Detail & Related papers  (2024-01-02T01:16:52Z)
• SOCI^+: An Enhanced Toolkit for Secure OutsourcedComputation on Integers [50.608828039206365]
  We propose SOCI+ which significantly improves the performance of SOCI. SOCI+ employs a novel (2, 2)-threshold Paillier cryptosystem with fast encryption and decryption as its cryptographic primitive. Compared with SOCI, our experimental evaluation shows that SOCI+ is up to 5.4 times more efficient in computation and 40% less in communication overhead.
  arXiv  Detail & Related papers  (2023-09-27T05:19:32Z)
• When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing [75.75419308975746]
  This work proposes a vertical federated learning architecture based on variational quantum circuits to demonstrate the competitive performance of a quantum-enhanced pre-trained BERT model for text classification. Our experiments on intent classification show that our proposed BERT-QTC model attains competitive experimental results in the Snips and ATIS spoken language datasets.
  arXiv  Detail & Related papers  (2022-02-17T09:55:21Z)
• A reversible system based on hybrid toggle radius-4 cellular automata and its application as a block cipher [0.0]
  We create a block cipher algorithm called HCA using a hybrid cellular automata (CA) mechanism to attain reversibility. Several evaluations and analyses performed on the model are presented here.
  arXiv  Detail & Related papers  (2021-06-09T02:52:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.