arXiv subjects

Behrooz Razeghi

Publications and source records attributed to Behrooz Razeghi.

At least 19 recordsLinked to original sources

arXiv2026

Soft GRAND under Channel Switching and Drift

Under channel switching or drift, the posterior used to order soft GRAND queries can differ from the matched correction posterior, which can increase rank and finite-budget decoding error. We bound log query rank by matched posterior self-information plus positive log-posterior mismatch; exact random-subset collision probabilities yield GRANDAB error bounds. For switching among memoryless channels with capacity-achieving uniform input, a state-path mixture yields vanishing error uniformly over admissible paths below the minimum constituent capacity when log path-class size is sublinear. For drift, pilot refresh bounds mismatch and yields the continuous minimizer of a tracking upper bound. Generalized-Gaussian BPSK experiments evaluate both.

cs.IT↗

arXiv2026

Tail-Calibrated Soft-Output GRAND for Finite-Memory Noise-Effect Posteriors

In guessing random additive noise decoding (GRAND), memory in the hard-decision noise effect changes the likelihood order of candidate noise effects. In soft-output decoding, the same memory also affects the finite-block quantity determining the missing-list probability: the codebook-restricted posterior mass outside the current list. Existing correlation-aware GRAND methods exploit local dependence without interleaving, but their stopping and soft-output rules are not derived from finite-memory posterior tails. Soft-output GRAND (SOGRAND) derives random-codebook a posteriori probability (APP) estimates for GRAND lists, but does not provide finite-memory algorithms for posterior weights, partition functions, tail masses, or bitwise tail marginals for correlated noise-effect posteriors. We introduce Tail-Calibrated SOGRAND for binary additive channels whose ambient hard-decision noise-effect posterior, conditioned on received soft information, is represented by a finite-memory energy. The decoder enumerates candidate noise effects in nondecreasing posterior energy, queries codebook membership as in GRAND, computes posterior weights and tail masses by finite-state recursions, and estimates the unqueried codebook-restricted denominator as $p_qT_q$, where $T_q$ is the ambient posterior tail mass and $p_q$ is the remaining random-codebook occupancy probability. With exact enumeration and no abandonment, the first listed codeword is ML under the likelihood model defining the posterior energy. We also prove an ambient posterior-tail abandonment bound and, separately, conditional unbiasedness, variance, and concentration bounds for the random-codebook missing-list estimator. The same posterior-tail decomposition gives blockwise APP estimates, missing-list probabilities, and bitwise APP log-likelihood ratios (LLRs) for finite-memory noise-effect posteriors.

cs.IT↗

arXiv2026

Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective

Across law, education, policy analysis, and public moral argumentation, LLM outputs are being used often for work that requires interpretations to be justified with textual evidence and explicit normative standards. Yet a recurrent failure mode -- what I call \textit{interpretive misplacement} -- is that model-generated readings get treated as settled meanings without an explicit interpretive frame (sources, scope constraints, normative commitments), without preserving defensible alternatives, and without provenance that lets readers find the supporting passages. In such settings, the risk is not only factual error but lost accountability: readers and institutions cannot reliably assess what an output commits them to, or on what basis. Drawing on philosophical hermeneutics, this paper discusses this risk and derives design principles for structuring human-AI co-interpretation. The paper also provides a structured synthesis of recent scholarship on hermeneutics and AI, organizing this emerging literature into a set of recurrent lines of argument and design-relevant gaps. LLM outputs are treated as candidate readings, whereas hermeneutic understanding is reserved for accountable human interpreters situated in disciplinary historical-linguistic traditions. Human-AI interaction is characterized as an AI-mediated interpretive loop. Hermeneutic understanding is distinguished from token-prediction--based text generation. On this basis, existing LLM techniques are reorganized into design patterns for hermeneutically responsible use in interpretive settings. Finally, the discussion turns to implications for legal practice, educational assessment and feedback, scholarly knowledge production, and public moral argumentation. It also treats digital hermeneutics as a literacy: the capacity to read AI-mediated texts by examining frames, provenance, and readings, and by contesting outputs.

cs.AI↗

arXiv2026

Low-Pathwidth GRAND: Exact Likelihood-Ordered Enumeration for BPSK Transmission over Correlated Gaussian Noise

The finite-block maximum-likelihood (ML) guarantee of soft-input GRAND requires querying noise-effect patterns in nonincreasing conditional-likelihood order. Under correlated Gaussian noise, additive reliability metrics and independent-block approximations need not preserve this order because the matched metric contains cross-coordinate interactions; the first codebook hit need not induce an ML codeword. We develop Low-Pathwidth GRAND (LP-GRAND) for binary phase-shift keying (BPSK) with precision matrix $Q$. The candidate-dependent part of the Gaussian negative log-likelihood is an observation-dependent quadratic pseudo-Boolean energy whose interaction graph has edge $\{i,j\}$ exactly when $Q_{ij}\neq0$. If $Q$ has half-bandwidth at most $\nu$, this energy admits a trellis with at most $2^\nu$ states per layer; a path decomposition of width $w$ yields at most $2^{w+1}$ bag assignments per layer. In real arithmetic, suffix dynamic programming and best-first complete-path enumeration enumerate patterns in nondecreasing energy. With complete enumeration and no abandonment, the first codebook hit induces an ML codeword for any nonempty binary codebook with equiprobable codewords. LP-GRAND agreed with exhaustive codeword ML in all $10{,}000$ frames for two $[20,12]$ codes. At nominal $E_b/N_0=2$ dB, its empirical BLER was lower than that of each block-based approximation for six $[64,52]$ codes.

cs.IT↗

arXiv2026

ScoreShield: Differentially Private Release of Similarity Scores

A growing number of applications, such as biometrics and retrieval-augmented generation (RAG), rely on cosine similarity scores computed between vector embeddings of text, images, or audio. These systems return similarity scores through their APIs for ranking and verification. However, such releases can leak information about individual records and enable membership inference attacks. While differential privacy (DP) provides a principled metric for quantifying attack risks, na\"ive application of DP mechanisms---such as adding i.i.d. Gaussian noise to vector entries---leads to excessive distortion (i.e., low utility) at a given privacy constraint that scales poorly with the number of released scores. We propose \textsc{ScoreShield}, a perturb-then-project mechanism that adds Gaussian noise calibrated to global sensitivity of the chosen score release regime and then projects the result onto the feasibility set of valid cosine objects. \textsc{ScoreShield} satisfies $(\varepsilon,\delta)$-DP for releasing similarity score vectors and Gram matrices. We provide utility guarantees for the exact Frobenius metric projection used in the risk analysis, and prove convergence to feasibility for the practical averaged alternating-projection solver used for large-scale Gram releases. For full pairwise cosine Gram release under record-level replacement adjacency, the exact-projection bound improves the $n$-dependence of squared Frobenius risk from $\Theta(n^3)$ for the na\"ive Gaussian baseline to $\mathcal{O}(n^2)$ for fixed privacy parameters, with sharper local bounds at low-rank Grams. We evaluate the mechanism across RAG, face recognition, semantic retrieval, image similarity, and recommender-system tasks.

cs.IR↗

arXiv2026

On the Capacity of Distinguishable Synthetic Identity Generation under Face Verification

Synthetic face generators can produce many nominal identities, but nominal count does not determine how many are jointly distinguishable under a specified verification rule. We define finite-dimensional capacity as the supremum of codebook sizes over distinct latent identity codes whose induced identity-conditional embedding distributions satisfy per-identity genuine acceptance and pairwise impostor non-match constraints. For deterministic view-invariant pipelines, fixed-code capacity equals the spherical-code cardinality over the realizable embedding set and reduces to the classical spherical-code cardinality when every sphere direction is realizable. For stochastic identity-conditional embedding distributions concentrated with probability at least $1-\eta$ in spherical caps of angular radius $\rho$, we derive a sufficient center-separation condition, spherical-code capacity lower bounds under full angular expressivity, and positive asymptotic lower-bound exponents for dimension-indexed pipeline families. We also derive prior-constrained random-code lower bounds from pairwise center-separation failure probabilities. When each identity-conditional embedding distribution has support equal to a spherical cap of angular radius $\rho$, we derive necessary zero-error geometric conditions and, for $2\rho<\arccos(\tau)$ under full $\rho$-cap angular expressivity, show that the restricted zero-error capacity equals the classical spherical-code cardinality at minimum angle $\arccos(\tau)+2\rho$. For finite repeated-view samples, a maximum clique in the resulting compatibility graph identifies the largest sampled subset satisfying all empirical genuine and pairwise impostor constraints. We evaluate this sample-restricted quantity on a deterministically selected DigiFace-1M subset under three fixed recognizers with identity-disjoint in-domain threshold calibration.

cs.IT↗

arXiv2026

Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment

AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when they are too broad to settle a situation, or when the relevant facts are unclear, an additional act of judgment is required. This paper analyzes that step through the lens of hermeneutics and argues that alignment therefore includes an interpretive component: it involves context-sensitive judgments about how principles should be read, applied, and prioritized in practice. We connect this claim to recent empirical findings showing that a substantial portion of preference-labeling data falls into cases of principle conflict or indifference, where the principle set does not uniquely determine a decision. We then draw an operational consequence: because such judgments are expressed in behavior, many alignment-relevant choices appear only in the distribution of responses a model generates at deployment time. To formalize this point, we distinguish deployment-induced and corpus-induced evaluation and show that off-policy audits can fail to capture alignment-relevant failures when the two response distributions differ. We argue that principle-specified alignment includes a context-dependent interpretive component.

cs.AI↗

arXiv2024

Synthetic to Authentic: Transferring Realism to 3D Face Renderings for Boosting Face Recognition

In this paper, we investigate the potential of image-to-image translation (I2I) techniques for transferring realism to 3D-rendered facial images in the context of Face Recognition (FR) systems. The primary motivation for using 3D-rendered facial images lies in their ability to circumvent the challenges associated with collecting large real face datasets for training FR systems. These images are generated entirely by 3D rendering engines, facilitating the generation of synthetic identities. However, it has been observed that FR systems trained on such synthetic datasets underperform when compared to those trained on real datasets, on various FR benchmarks. In this work, we demonstrate that by transferring the realism to 3D-rendered images (i.e., making the 3D-rendered images look more real), we can boost the performance of FR systems trained on these more photorealistic images. This improvement is evident when these systems are evaluated against FR benchmarks utilizing real-world data, thereby paving new pathways for employing synthetic data in real-world applications.

cs.CV↗

arXiv2024

Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition

In this study, we apply the information-theoretic Privacy Funnel (PF) model to face recognition and develop a method for privacy-preserving representation learning within an end-to-end trainable framework. Our approach addresses the trade-off between utility and obfuscation of sensitive information under logarithmic loss. We study the integration of information-theoretic privacy principles with representation learning, with a particular focus on face recognition systems. We also highlight the compatibility of the proposed framework with modern face recognition networks such as AdaFace and ArcFace. In addition, we introduce the Generative Privacy Funnel ($\mathsf{GenPF}$) model, which extends the traditional discriminative PF formulation, referred to here as the Discriminative Privacy Funnel ($\mathsf{DisPF}$). The proposed $\mathsf{GenPF}$ model extends the privacy-funnel framework to generative formulations under information-theoretic and estimation-theoretic criteria. Complementing these developments, we present the deep variational PF (DVPF) model, which yields a tractable variational bound for measuring information leakage and enables optimization in deep representation-learning settings. The DVPF framework, associated with both the $\mathsf{DisPF}$ and $\mathsf{GenPF}$ models, also clarifies connections with generative models such as variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models. Finally, we validate the framework on modern face recognition systems and show that it provides a controllable privacy--utility trade-off while substantially reducing leakage about sensitive attributes. To support reproducibility, we also release a PyTorch implementation of the proposed framework.

cs.LG↗

arXiv2024

Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition

In this study, we harness the information-theoretic Privacy Funnel (PF) model to develop a method for privacy-preserving representation learning using an end-to-end training framework. We rigorously address the trade-off between obfuscation and utility. Both are quantified through the logarithmic loss, a measure also recognized as self-information loss. This exploration deepens the interplay between information-theoretic privacy and representation learning, offering substantive insights into data protection mechanisms for both discriminative and generative models. Importantly, we apply our model to state-of-the-art face recognition systems. The model demonstrates adaptability across diverse inputs, from raw facial images to both derived or refined embeddings, and is competent in tasks such as classification, reconstruction, and generation.

cs.CV↗

arXiv2022

Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility

Bottleneck problems are an important class of optimization problems that have recently gained increasing attention in the domain of machine learning and information theory. They are widely used in generative models, fair machine learning algorithms, design of privacy-assuring mechanisms, and appear as information-theoretic performance bounds in various multi-user communication problems. In this work, we propose a general family of optimization problems, termed as complexity-leakage-utility bottleneck (CLUB) model, which (i) provides a unified theoretical framework that generalizes most of the state-of-the-art literature for the information-theoretic privacy models, (ii) establishes a new interpretation of the popular generative and discriminative models, (iii) constructs new insights to the generative compression models, and (iv) can be used in the fair generative models. We first formulate the CLUB model as a complexity-constrained privacy-utility optimization problem. We then connect it with the closely related bottleneck problems, namely information bottleneck (IB), privacy funnel (PF), deterministic IB (DIB), conditional entropy bottleneck (CEB), and conditional PF (CPF). We show that the CLUB model generalizes all these problems as well as most other information-theoretic privacy models. Then, we construct the deep variational CLUB (DVCLUB) models by employing neural networks to parameterize variational approximations of the associated information quantities. Building upon these information quantities, we present unified objectives of the supervised and unsupervised DVCLUB models. Leveraging the DVCLUB model in an unsupervised setup, we then connect it with state-of-the-art generative models, such as variational auto-encoders (VAEs), generative adversarial networks (GANs), as well as the Wasserstein GAN (WGAN), Wasserstein auto-encoder (WAE), and adversarial auto-encoder (AAE) models through the optimal transport (OT) problem. We then show that the DVCLUB model can also be used in fair representation learning problems, where the goal is to mitigate the undesired bias during the training phase of a machine learning model. We conduct extensive quantitative experiments on colored-MNIST and CelebA datasets, with a public implementation available, to evaluate and analyze the CLUB model.

cs.LG↗

arXiv2021

Variational Leakage: The Role of Information Complexity in Privacy Leakage

We study the role of information complexity in privacy leakage about an attribute of an adversary's interest, which is not known a priori to the system designer. Considering the supervised representation learning setup and using neural networks to parameterize the variational bounds of information quantities, we study the impact of the following factors on the amount of information leakage: information complexity regularizer weight, latent space dimension, the cardinalities of the known utility and unknown sensitive attribute sets, the correlation between utility and sensitive attributes, and a potential bias in a sensitive attribute of adversary's interest. We conduct extensive experiments on Colored-MNIST and CelebA datasets to evaluate the effect of information complexity on the amount of intrinsic leakage.

cs.LG↗

arXiv2021

Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation

In this paper, we propose a framework for privacy-preserving approximate near neighbor search via stochastic sparsifying encoding. The core of the framework relies on sparse coding with ambiguation (SCA) mechanism that introduces the notion of inherent shared secrecy based on the support intersection of sparse codes. This approach is `fairness-aware', in the sense that any point in the neighborhood has an equiprobable chance to be chosen. Our approach can be applied to raw data, latent representation of autoencoders, and aggregated local descriptors. The proposed method is tested on both synthetic i.i.d data and real large-scale image databases.

cs.IR↗

arXiv2020

On Perfect Obfuscation: Local Information Geometry Analysis

We consider the problem of privacy-preserving data release for a specific utility task under perfect obfuscation constraint. We establish the necessary and sufficient condition to extract features of the original data that carry as much information about a utility attribute as possible, while not revealing any information about the sensitive attribute. This problem formulation generalizes both the information bottleneck and privacy funnel problems. We adopt a local information geometry analysis that provides useful insight into information coupling and trajectory construction of spherical perturbation of probability mass functions. This analysis allows us to construct the modal decomposition of the joint distributions, divergence transfer matrices, and mutual information. By decomposing the mutual information into orthogonal modes, we obtain the locally sufficient statistics for inferences about the utility attribute, while satisfying perfect obfuscation constraint. Furthermore, we develop the notion of perfect obfuscation based on $χ^2$-divergence and Kullback-Leibler divergence in the Euclidean information geometry.

cs.IT↗

arXiv2020

BSROne: Binary Search with Routing of O(1); A Scalable Circular Design for Distributed Networks

Peer-to-Peer (P2P) networks as distributed solutions are used in a variety of applications. Based on the type of routing for queries among their nodes, they are classified into three groups: structured, unstructured and small-world P2P networks. Each of these categories has its own applications and benefits. Structured networks by using Distributed Hash Tables (DHT) can forward request search queries more efficiently. These networks usually organize a specific topology and make a geometrical shape. A circular topology is a prevalent design which was first introduced by Chord. In this paper, we propose BSROne, a circular structured P2P design which attempts to consider several shortcomings in the current networks. In our proposed method, we want to achieve O(1) routing time without requiring all of the nodes to know about each other. By removing the real connections between nodes and tying all of them with super-nodes, we could reduce the number of overheads that are essential to maintain the connectivity between nodes in such networks. Furthermore, we gave the network an ability to scale up by introducing one layer above super-nodes. We achieved this by emulating the design of binary search algorithm for supreme-nodes. In this paper, at first we introduce a design where fixed super-nodes with unlimited resources are given to the distributed network. In the next step, we explain how it can manage to work as a P2P application. We finally discuss the possibility of removing the scalability issue in a P2P environment for our design.

cs.NI↗

arXiv2020

Privacy-Preserving Image Sharing via Sparsifying Layers on Convolutional Groups

We propose a practical framework to address the problem of privacy-aware image sharing in large-scale setups. We argue that, while compactness is always desired at scale, this need is more severe when trying to furthermore protect the privacy-sensitive content. We therefore encode images, such that, from one hand, representations are stored in the public domain without paying the huge cost of privacy protection, but ambiguated and hence leaking no discernible content from the images, unless a combinatorially-expensive guessing mechanism is available for the attacker. From the other hand, authorized users are provided with very compact keys that can easily be kept secure. This can be used to disambiguate and reconstruct faithfully the corresponding access-granted images. We achieve this with a convolutional autoencoder of our design, where feature maps are passed independently through sparsifying transformations, providing multiple compact codes, each responsible for reconstructing different attributes of the image. The framework is tested on a large-scale database of images with public implementation available.

cs.CV↗

arXiv2019

Single-Component Privacy Guarantees in Helper Data Systems and Sparse Coding with Ambiguation

We investigate the privacy of two approaches to (biometric) template protection: Helper Data Systems and Sparse Ternary Coding with Ambiguization. In particular, we focus on a privacy property that is often overlooked, namely how much leakage exists about one specific binary property of one component of the feature vector. This property is e.g. the sign or an indicator that a threshold is exceeded. We provide evidence that both approaches are able to protect such sensitive binary variables, and discuss how system parameters need to be set.

cs.IT↗

arXiv2019

Reconstruction of Privacy-Sensitive Data from Protected Templates

In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise to satisfy the privacy-utility trade-off requirements. The theoretical privacy-preserving properties of STCA have been validated on synthetic data. However, the applicability of STCA to real data and potential threats linked to reconstruction based on recent deep reconstruction algorithms are still open problems. Our results demonstrate that STCA still achieves the claimed theoretical performance when facing deep reconstruction attacks for the synthetic i.i.d. data, while for real images special measures are required to guarantee proper protection of the templates.

cs.LG↗