arXiv subjects

Ferhat Erata

Publications and source records attributed to Ferhat Erata.

17 recordsLinked to original sources

arXiv2026

Beyond Solver Verdicts: Generative Reward Models for Autoformalization

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict reference-equivalence to a designated formalization. We formalize this vulnerability as Verdict-Preserving-Unfaithfulness (VPU): a failure mode where an incorrect encoding executes successfully and matches the expected verdict. We theoretically prove that structural, verdict-only verification heuristics are mathematically bounded to chance-level detection on these deceptively valid traces. To resolve this, we introduce Generative Verification (GenV), which distills an offline Z3-equivalence oracle into a reference-free, continuous reference-equivalence score by repurposing the language model's native vocabulary space. Mechanistic analysis via decision-projected logit lenses and sparse autoencoders shows this generative readout natively extracts precise spatial error coordinates without explicit localization training. Empirically, our oracle-mined verifier (GenV+HN) achieves 0.961 AUROC in reference-equivalence verification, generalizes zero-shot across unseen translators and divergent formal styles, and yields an 11.3-point downstream accuracy gain in agentic test-time compute allocation.

cs.LG↗

arXiv2026

Stratified Consistency Distillation for Natural Language Formalization

Neurosymbolic reasoning has shown promising success in addressing complex reasoning tasks by combining large language models (LLMs) and symbolic solvers. While this approach shows promise, a fundamental challenge remains: improving the accuracy of translations from natural language to logical formulas. Current methods predominantly rely on prompt engineering, which is difficult to scale across different domains and input formats. Drawing inspiration from the success of fine-tuning in other model adaptation and alignment applications, we propose a fine-tuning-based Stratified Consistency Distillation approach: (1) We generate K logical translations per input using a frontier LLM and cluster them by semantic equivalence (2) Based on the entropy level, we apply majority voting (low entropy), LLM-as-a-Judge (medium entropy), or unification/abstention (high entropy), and (3) fine-tune a smaller model using the selected pseudo-labels. Our experiments show significant and consistent improvements in both Pass@K and our novel Equivalent Logical Similarity metrics, demonstrating the potential of advancing logical translation through consistency distillation.

cs.CL↗

arXiv2026

Fidelity Probes for Specification--Code Alignment

We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a candidate specification. The fraction of agreeing probes, which we call the fidelity, decomposes into contradiction and coverage-gap rates that drive targeted spec edits to convergence. On a 15-program, roughly 12k-line COBOL benchmark (AWS CardDemo), we raise frozen-test specification fidelity from 0.63 to 0.94 over eight iterations, with the plateau location predicted by a two-state Markov fixed point $F^\dagger$ from just four iterations of rate data. Probes come from an LLM reading the code or from a static-analysis pipeline over its control-flow, data-flow, and system-dependence graphs, with a tunable mixture. A probe-resampling protocol with a frozen held-out set gives a Hoeffding-bounded overfitting discriminant; our measured train/test gap stays more than an order of magnitude below this envelope. Three graph-grounded mixtures lift fidelity by +16 to +30 points; cross-distribution evaluation shows the LLM and symbolic channels are empirically complementary. A cross-family generator sweep on five independent LLM lineages (Anthropic, DeepSeek, Google, Alibaba, OpenAI) confirms the convergence behaviour is not tied to any single model family: three of five non-Claude generators produce trajectories consistent with the Markov fixed-point prediction, and the frozen-test protocol actively falsifies the two generators whose probe distributions drift across iterations. The method applies to any pair of artifacts that are supposed to describe the same behaviour.

cs.LG↗

arXiv2026

Learning How to Cube

Despite the effectiveness of Cube-and-Conquer (C&C) for solving challenging Boolean Satisfiability (SAT) problems, no prior work has shown that transformer-based models can learn effective cubing heuristics. We introduce a neuro-symbolic post-training framework for this task. We design an MCTS-based data curation pipeline that uses symbolic heuristics to explore splitting decisions over SAT competition formulas, producing preference data grounded in solver statistics and augmented with reasoning traces from a teacher model. Our two-stage post-training, supervised fine-tuning (SFT) followed by direct preference optimization (DPO), enables a 4B-parameter model to achieve a pass@5 score of 53 on 100 SAT competition benchmarks, surpassing frontier LLMs such as Claude-Sonnet-4 (50) and matching the best symbolic heuristic (53). Ablations show that SFT alone improves pass@5 from 46 to 51, with DPO adding 2 additional benchmarks; an entropy/agreement ablation on realized first-cube decisions further shows that SFT, not DPO, accounts for the root-level decision diversity that produces complementary per-run coverage over deterministic symbolic methods. This demonstrates that transformers can be trained to make effective cubing decisions in a domain traditionally dominated by symbolic methods.

cs.LG↗

arXiv2025

A Neurosymbolic Approach to Natural Language Formalization and Verification

Large Language Models perform well at natural language interpretation and reasoning, but their lack of formal correctness guarantees limits their adoption in regulated industries like finance and health-care that operate under strict policies. To address this limitation, we launched Automated Reasoning checks (ARc): a public service that (1) uses LLMs with optional human guidance to formalize natural language policies, allowing fine-grained control of the formalization process, and (2) uses inference-time autoformalization to validate logical correctness of natural language statements against those policies. ARc performs multiple redundant formalization steps at inference time, checking the formalizations for semantic equivalence. Our benchmarks show that ARc exceeds 99% soundness and achieves a near-zero false positive rate in identifying logical validity. Our approach produces auditable artifacts that substantiate the verification outcomes and can be used to improve the original text. ARc is the first commercial offering from a major cloud provider to integrate automated reasoning into a generative AI guardrail.

cs.CL↗

arXiv2024

Learning Randomized Reductions

Randomized self-reductions (RSRs) express $f(x)$ using $f$ evaluated at random correlated points, enabling self-correcting programs, instance-hiding protocols, and applications in complexity theory and cryptography. Yet discovering RSRs has required manual expert derivation for over 40 years, limiting their practical use. We present Bitween for automated RSR learning. First, we formalize RSR learning with sample complexity analysis under correlated sampling. Second, we develop Vanilla Bitween, which integrates multiple backends (linear regression, genetic programming, symbolic regression, and mixed-integer programming). The linear regression backend outperforms the others, discovering RSRs for 43 of 80 functions (54%) in RSR-Bench, our benchmark suite, including the first known reduction for sigmoid. Third, we introduce Agentic Bitween, a neuro-symbolic approach where LLM agents propose novel query functions beyond the fixed set ($x+r$, $x-r$, $x \cdot r$, $x$, $r$) in prior work. Agentic Bitween discovers RSRs for 64 of 80 functions (80%), outperforming pure neural baselines in both RSR discovery and verification accuracy.

cs.LG↗

arXiv2024

Scheherazade: Evaluating Chain-of-Thought Math Reasoning in LLMs with Chain-of-Problems

Benchmarks are critical for measuring Large Language Model (LLM) reasoning capabilities. Some benchmarks have even become the de facto indicator of such capabilities. However, as LLM reasoning capabilities improve, existing widely-used benchmarks such as GSM8K marginally encapsulate model reasoning differentials - most state-of-the-art models for example achieve over 94% accuracy on the GSM8K dataset (paperwithcode, 2024). While constructing harder benchmarks is possible, their creation is often manual, expensive, and unscalable. As such, we present Scheherazade, an automated approach to produce large quantities of challenging mathematical reasoning benchmarks by logically chaining a small starting set of problems. We propose two different chaining methods, forward chaining and backward chaining, which include randomized branching techniques to generate complex reasoning problems. We apply Scheherazade on GSM8K to create GSM8K-Scheherazade and evaluate 3 frontier LLMs and OpenAI's o1-preview on it. We show that while other frontier models' performance declines precipitously at only a few questions chained, our evaluation suggests o1-preview's performance persists, with the flagship OpenAI model the only one to perform better at backward reasoning. Our data and code are available at https://github.com/YoshikiTakashima/scheherazade-code-data.

cs.CL↗

arXiv2024

Systematic Use of Random Self-Reducibility against Physical Attacks

This work presents a novel, black-box software-based countermeasure against physical attacks including power side-channel and fault-injection attacks. The approach uses the concept of random self-reducibility and self-correctness to add randomness and redundancy in the execution for protection. Our approach is at the operation level, is not algorithm-specific, and thus, can be applied for protecting a wide range of algorithms. The countermeasure is empirically evaluated against attacks over operations like modular exponentiation, modular multiplication, polynomial multiplication, and number theoretic transforms. An end-to-end implementation of this countermeasure is demonstrated for RSA-CRT signature algorithm and Kyber Key Generation public key cryptosystems. The countermeasure reduced the power side-channel leakage by two orders of magnitude, to an acceptably secure level in TVLA analysis. For fault injection, the countermeasure reduces the number of faults to 95.4% in average.

cs.CR↗

arXiv2024

Integrating Static Code Analysis Toolchains

This paper proposes an approach for a tool-agnostic and heterogeneous static code analysis toolchain in combination with an exchange format. This approach enhances both traceability and comparability of analysis results. State of the art toolchains support features for either test execution and build automation or traceability between tests, requirements and design information. Our approach combines all those features and extends traceability to the source code level, incorporating static code analysis. As part of our approach we introduce the "ASSUME Static Code Analysis tool exchange format" that facilitates the comparability of different static code analysis results. We demonstrate how this approach enhances the usability and efficiency of static code analysis in a development process. On the one hand, our approach enables the exchange of results and evaluations between static code analysis tools. On the other hand, it enables a complete traceability between requirements, designs, implementation, and the results of static code analysis. Within our approach we also propose an OSLC specification for static code analysis tools and an OSLC communication framework.

cs.SE↗

arXiv2024

A Tool for Automated Reasoning About Traces Based on Configurable Formal Semantics

We present Tarski, a tool for specifying configurable trace semantics to facilitate automated reasoning about traces. Software development projects require that various types of traces be modeled between and within development artifacts. For any given artifact (e.g., requirements, architecture models and source code), Tarski allows the user to specify new trace types and their configurable semantics, while, using the semantics, it automatically infers new traces based on existing traces provided by the user, and checks the consistency of traces. It has been evaluated on three industrial case studies in the automotive domain (https://modelwriter.github.io/Tarski/).

cs.SE↗

arXiv2024

AlloyInEcore: Embedding of First-Order Relational Logic into Meta-Object Facility for Automated Model Reasoning

We present AlloyInEcore, a tool for specifying metamodels with their static semantics to facilitate automated, formal reasoning on models. Software development projects require that software systems be specified in various models (e.g., requirements models, architecture models, test models, and source code). It is crucial to reason about those models to ensure the correct and complete system specifications. AlloyInEcore allows the user to specify metamodels with their static semantics, while, using the semantics, it automatically detects inconsistent models, and completes partial models. It has been evaluated on three industrial case studies in the automotive domain (https://modelwriter.github.io/AlloyInEcore/).

cs.SE↗

arXiv2024

ModelWriter: Text & Model-Synchronized Document Engineering Platform

The ModelWriter platform provides a generic framework for automated traceability analysis. In this paper, we demonstrate how this framework can be used to trace the consistency and completeness of technical documents that consist of a set of System Installation Design Principles used by Airbus to ensure the correctness of aircraft system installation. We show in particular, how the platform allows the integration of two types of reasoning: reasoning about the meaning of text using semantic parsing and description logic theorem proving; and reasoning about document structure using first-order relational logic and finite model finding for traceability analysis.

cs.SE↗

arXiv2024

Quantum Circuit Reconstruction from Power Side-Channel Attacks on Quantum Computer Controllers

The interest in quantum computing has grown rapidly in recent years, and with it grows the importance of securing quantum circuits. A novel type of threat to quantum circuits that dedicated attackers could launch are power trace attacks. To address this threat, this paper presents first formalization and demonstration of using power traces to unlock and steal quantum circuit secrets. With access to power traces, attackers can recover information about the control pulses sent to quantum computers. From the control pulses, the gate level description of the circuits, and eventually the secret algorithms can be reverse engineered. This work demonstrates how and what information could be recovered. This work uses algebraic reconstruction from power traces to realize two new types of single trace attacks: per-channel and total power attacks. The former attack relies on per-channel measurements to perform a brute-force attack to reconstruct the quantum circuits. The latter attack performs a single-trace attack using Mixed-Integer Linear Programming optimization. Through the use of algebraic reconstruction, this work demonstrates that quantum circuit secrets can be stolen with high accuracy. Evaluation on 32 real benchmark quantum circuits shows that our technique is highly effective at reconstructing quantum circuits. The findings not only show the veracity of the potential attacks, but also the need to develop new means to protect quantum circuits from power trace attacks. Throughout this work real control pulse information from real quantum computers is used to demonstrate potential attacks based on simulation of collection of power traces.

cs.CR↗

arXiv2023

Classification of Quantum Computer Fault Injection Attacks

The rapid growth of interest in quantum computing has brought about the need to secure these powerful machines against a range of physical attacks. As qubit counts increase and quantum computers achieve higher levels of fidelity, their potential to execute novel algorithms and generate sensitive intellectual property becomes more promising. However, there is a significant gap in our understanding of the vulnerabilities these computers face in terms of security and privacy attacks. Among the potential threats are physical attacks, including those orchestrated by malicious insiders within data centers where the quantum computers are located, which could compromise the integrity of computations and resulting data. This paper presents an exploration of fault-injection attacks as one class of physical attacks on quantum computers. This work first introduces a classification of fault-injection attacks and strategies, including the domain of fault-injection attacks, the fault targets, and fault manifestations in quantum computers. The resulting classification highlights the potential threats that exist. By shedding light on the vulnerabilities of quantum computers to fault-injection attacks, this work contributes to the development of robust security measures for this emerging technology.

cs.CR↗

arXiv2023

Exploration of Quantum Computer Power Side-Channels

With the rapidly growing interest in quantum computing also grows the importance of securing these quantum computers from various physical attacks. Constantly increasing qubit counts and improvements to the fidelity of the quantum computers hold great promise for the ability of these computers to run novel algorithms with highly sensitive intellectual property. However, in today's cloud-based quantum computer setting, users lack physical control over the computers. Physical attacks, such as those perpetrated by malicious insiders in data centers, could be used to extract sensitive information about the circuits being executed on these computers. Indeed, this work shows for the first time that power-based side-channel attacks could be deployed against quantum computers. Such attacks can be used to recover information about the control pulses sent to these computers. By analyzing these control pulses, attackers can reverse-engineer the equivalent gate-level description of the circuits, and possibly even the secret algorithms being run. This work introduces five new types of attacks, and evaluates them using control pulse information available from cloud-based quantum computers. This work demonstrates how and what circuits could be recovered, and then in turn how to defend from the newly demonstrated side-channel attacks on quantum~computers.

cs.CR↗

arXiv2023

Towards Automated Detection of Single-Trace Side-Channel Vulnerabilities in Constant-Time Cryptographic Code

Although cryptographic algorithms may be mathematically secure, it is often possible to leak secret information from the implementation of the algorithms. Timing and power side-channel vulnerabilities are some of the most widely considered threats to cryptographic algorithm implementations. Timing vulnerabilities may be easier to detect and exploit, and all high-quality cryptographic code today should be written in constant-time style. However, this does not prevent power side-channels from existing. With constant time code, potential attackers can resort to power side-channel attacks to try leaking secrets. Detecting potential power side-channel vulnerabilities is a tedious task, as it requires analyzing code at the assembly level and needs reasoning about which instructions could be leaking information based on their operands and their values. To help make the process of detecting potential power side-channel vulnerabilities easier for cryptographers, this work presents Pascal: Power Analysis Side Channel Attack Locator, a tool that introduces novel symbolic register analysis techniques for binary analysis of constant-time cryptographic algorithms, and verifies locations of potential power side-channel vulnerabilities with high precision. Pascal is evaluated on a number of implementations of post-quantum cryptographic algorithms, and it is able to find dozens of previously reported single-trace power side-channel vulnerabilities in these algorithms, all in an automated manner.

cs.CR↗

arXiv2022

ETAP: Energy-aware Timing Analysis of Intermittent Programs

Energy harvesting battery-free embedded devices rely only on ambient energy harvesting that enables stand-alone and sustainable IoT applications. These devices execute programs when the harvested ambient energy in their energy reservoir is sufficient to operate and stop execution abruptly (and start charging) otherwise. These intermittent programs have varying timing behavior under different energy conditions, hardware configurations, and program structures. This paper presents Energy-aware Timing Analysis of intermittent Programs (ETAP), a probabilistic symbolic execution approach that analyzes the timing and energy behavior of intermittent programs at compile time. ETAP symbolically executes the given program while taking time and energy cost models for ambient energy and dynamic energy consumption into account. We evaluated ETAP on several intermittent programs and compared the compile-time analysis results with executions on real hardware. The results show that ETAP's normalized prediction accuracy is 99.5%, and it speeds up the timing analysis by at least two orders of magnitude compared to manual testing.

cs.SE↗