Searcharxiv⌕ Search

arXiv subjects

Habibur Rahaman

Publications and source records attributed to Habibur Rahaman.

15 recordsLinked to original sources

The distribution of $αp$ modulo one in short intervals

Let $\|x\|$ denote the distance from a real number $x$ to the nearest integer, and let $α$ be any irrational number and $β_0$ any real number. We prove that there exist infinitely many $X$ such that for $Y=X^γ/2$ with $7/12<γ\le 1$ and $0<θ<\min \{(12γ-7)/24, 1/9\}$, there is a prime $p$ satisfying $$ \|αp+β_0\|<X^{-θ},\quad X-Y<p<X. $$ Moreover, we obtain an asymptotic formula for the number of such primes. In particular, if $α$ has a continued fraction expansion with bounded partial quotients, then this asymptotic holds for all sufficiently large $X$. Our result improves upon a previous result of Baier and Roy by extending the admissible range of the short interval parameter from $2/3<γ\le 1$ to $7/12<γ\le 1$, reaching Huxley's classical range for primes in short intervals, and also improves the exponent $θ$ for $2/3\leγ\le3/4$. The improvement is obtained by adapting a recent result of Maynard, Pandey, and Radziwiłł on exponential sums over primes.

math.NT↗

SANAI: Secure ECC Distributed Keyed Parity Embedded in Weights for Protecting Neural Networks against Bit-Flip Attacks

Quantized neural networks store weights in dense memory, where bit flips caused by voltage scaling, aging, radiation, or deliberate attacks such as RowHammer can severely degrade model behavior. A single corrupted high-order bit can cause misclassifications or nonsensical language-model outputs. Embedded error-correcting codes (ECC) avoid dedicated parity storage by hiding parity within model weights, but existing schemes embed uniformly across layers and bit planes, leave parity unsecured, and tolerate bit-error rates (BERs) only up to about 6%. An adversary aware of sensitive weights and the ECC scheme can also bypass protection by exceeding the correction capability of targeted codewords. We propose SANAI, a sensitivity-guided, bit-plane-selective scheme that protects critical model weights against bit flips with zero additional parity-storage overhead. SANAI secures parity through keyed embedding across a two-dimensional weight space: spread-transform dither modulation binds parity to a secret key, and keyed interleaving disperses concentrated attacks across codewords. We derive a survival law showing that robustness is governed by the correctable fraction t/n rather than by t alone, and a closed-form bound on the protectable fraction of a model. As a streaming checker on an 8x8 systolic array, SANAI verifies weights on the load path with 0.41% area overhead and no additional memory. Across ten vision backbones, three quantization schemes, and ten language models from 82M to 13B parameters, SANAI stays within about one percentage point of clean accuracy at BERs up to 12%, twice the maximum of prior embedded-ECC approaches. It survives fine-tuning bit-exactly, neutralizes progressive and targeted bit-flip attacks, and exactly corrects AttentionBreaker and SilentStriker attacks.

cs.CR↗

LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks

The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry about a fifth of the damage a bit flip can do. This distribution decides the bit-flip tolerance of a model, the fraction of weights a code must cover and the bits each weight needs; existing schemes work with the distribution training leaves. We show that we can systematically modulate or alter the weight sensitivity distribution of a trained model, thereby shifting weights from one sensitivity bin to another. The sensitivity of a stored weight is the product of its gradient and the step a flip takes in the storage format, and LEAN adds a composite regularizer on both factors, a range term that bounds the flip step and a tail term that lowers the gradient of the most sensitive weights, with one coefficient λ setting how far the distribution moves. Ten epochs with the term, as a fine-tune or as the last epochs of training, shrink the sensitive tail 5 to 13 times on nine vision models (ResNet-18, ResNet-50, VGG-16 on CIFAR-10, CIFAR-100, ImageNet) within 0.5 points of accuracy; real flips confirm that the reshaped weights do less damage, a plain gradient-norm penalty does not reproduce the effect, and a preliminary extension to three small language models shows the same tail shaping. With a BCH code over 1% of the weights the model then survives 300 progressive bit-search flips in every training seed and 500 in two of three, where three of four published defenses with the same code fail by 300 and WCAT falls to 75% at 500. The reshaped distribution also cuts the parity for a fixed guarantee 3.7 times and makes a sensitivity-ordered 8/6/4/3-bit format affordable, which stores ImageNet ResNet-50 at a 3.29-bit weight payload, 2.4 times smaller than INT8, above the accuracy of LSQ at 3 bits.

cs.LG↗

BARE-AI: Bit-Flip Attack Resilience in AI Hardware through Built-in Performance Monitors

Deep Neural Networks (DNNs) are integral to many safety critical systems, yet they remain highly vulnerable to bit-flip attacks (BFAs), where a few memory level perturbations can drastically degrade accuracy. Existing defenses incur significant hardware overhead, depend on retraining, or fail against targeted flips. We propose BARE-AI, a runtime framework that detects, localizes, and mitigates BFAs during inference. BARE-AI introduces AI Performance Counters (APCs), lightweight hardware monitors in the accelerator datapath that capture per-layer activation statistics such as sparsity, entropy, kurtosis, and spectral shift. These are analyzed by the Predictive Unit for Layer Security Evaluation (PULSE), a compact detector trained offline as an ensemble of classifiers and realized on-chip as a small neural engine. For explainability and recovery, BARE-AI introduces an Activation Shift Index (ASI) for layer level fault localization and a z-score based repair that resets anomalous weights toward clean layer statistics. Across CNNs, Vision Transformers, and Large Language Models under random, targeted, adaptive, and magnitude based BFAs, BARE-AI achieves up to 98% detection accuracy on vision models and 74% to 95% on language models, restores near clean accuracy for CNNs and ViTs, and provides partial recovery for LLMs. Synthesized at 28nm, the monitoring infrastructure incurs under 3% energy, under 4% area, and about 10% latency overhead, with a configurable operating point that reduces latency overhead to about 6%. Unlike error correcting codes, whose redundancy grows with the number of tolerated flips, BARE-AI's overhead remains constant regardless of attack strength, making it attractive for resource constrained, safety critical edge applications such as autonomous systems, energy, and healthcare.

cs.CR↗

(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure

Modern machine learning (ML) pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current practices audit data and model artifacts or rely on file integrity checks, the execution environment remains implicitly trusted. This blind spot enables active threats where a malicious runtime module interacts directly with live training and inference dynamics: exploiting this interaction allows the Trojan to support complex objectives that are challenging for static code or binary modifications, achieving manipulations impossible for standard data and model level attacks. We expose this vulnerability by presenting AiSPY, a parasitic infrastructure Trojan that subverts MLsystems through an active observe and execute paradigm. Operating within the computation graph, AiSPY monitors transient tensor states to perform targeted, stealthy manipulations with negligible overhead. To violate confidentiality, the Trojan identifies all critical training hyperparameters and covertly exfiltrates them via model weights or output logits. To break integrity, it acts as a gradient amplifier: by observing steganographic triggers, it transforms other- wise weak data poisoning into effective backdoor attacks, increasing success rates from near zero to 100%. We further demonstrate broad extensibility across the machine learning lifecycle by validating auxiliary attacks in the appendix, including subpopulation label flipping, availability disruptions, and inference stage manipulations. Importantly, the evaluated malware scanners do not flag AiSPY because current public rule sets lack coverage for ML runtime Trojans, while the associated poisoned inputs and resulting compromised models bypass state-of-the-art inspection tools. We demonstrate the practicality of this threat with an implementation in the ONNX Runtime training and inference engines.

cs.CR↗

Diophantine approximation with sums of two squares II

Recently, the authors showed that for every irrational number $α$, there exist infinitely many positive integers $n$ represented by any given positive definite binary quadratic form $Q$, satisfying $||αn|| 0$. We also provided a quantitative version with a lower bound when the exponent $1/2-\varepsilon$ is replaced by a smaller exponent $γ<3/7-\varepsilon$. In this article, we establish a quantitative version for the exponent $1/2-\varepsilon$, where we confine ourselves to the particular case of sums of two squares.

math.NT↗

DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples

Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to align well with human perception, and only a few methods specifically explore perceptually aligned adversarial examples. Moreover, it remains unclear whether insights from Lp-constrained attacks can be effectively leveraged to improve perceptual efficacy. In this paper, we introduce DASH, a fully differentiable meta-attack framework that generates effective and perceptually aligned adversarial examples by strategically composing existing Lp-based attack methods. DASH operates in a multi-stage fashion: at each stage, it aggregates candidate adversarial examples from multiple base attacks using learned, adaptive weights and propagates the result to the next stage. A novel meta-loss function guides this process by jointly minimizing misclassification loss and perceptual distortion, enabling the framework to dynamically modulate the contribution of each base attack throughout the stages. We evaluate DASH on adversarially trained models across CIFAR-10, CIFAR-100, and ImageNet. Despite relying solely on Lp-constrained based methods, DASH significantly outperforms state-of-the-art perceptual attacks such as AdvAD, achieving higher attack success rates (e.g., 20.63% improvement) and superior visual quality, as measured by SSIM, LPIPS, and FID (improvements $\approx$ of 11, 0.015, and 5.7, respectively). Furthermore, DASH generalizes well to unseen defenses, making it a practical and strong baseline for evaluating robustness without requiring handcrafted adaptive attacks for each new defense.

cs.CV↗

Diophantine approximation with sums of two squares

For any given positive definite binary quadratic form $Q$ with integer coefficients, we establish two results on Diophantine approximation with integers represented by $Q$. Firstly, we show that for every irrational number $α$, there exist infinitely many positive integers $n$ represented by $Q$ and satisfying $||αn|| 0$. This is an easy consequence of a result by Cook on small fractional parts of diagonal quadratic forms. Secondly, we give a quantitative version with a lower bound of this result when the exponent $1/2-\varepsilon$ is replaced by any fixed $γ<3/7$. To this end, we use the Voronoi summation formula and a bound for bilinear forms with Kloosterman sums to fixed moduli by Kerr, Shparlinski, Wu and Xi.

math.NT↗

Diophantine approximation with integers having no large prime factors

Given any irrational number $α$, we show that for any $0<θ<6/17$, there are infinitely many $y$-smooth (friable) numbers $n$ such that $$\|nα\| < n^{-θ},$$ where $(\log n)^C\leq y\leq n$ for some large constant $C>0$. This improves the previous work of Baker, who obtained the exponent $1/3-2/(3C)+o(1)$ in the case of $y\geq (\log n)^C$, and that of Yau, who obtained the exponent $1/3$ when $y=n^{o(1)}$. Our proof is based on the dispersion method together with arithmetic inputs coming from the average bounds for Kloosterman sums over smooth numbers.

math.NT↗

Diophantine Approximation with Piatetski-Shapiro Primes

We prove that for every irrational number $α$, real number $β$, real number $c$ satisfying $1<c<9/8$ and positive real number $θ$ satisfying $θ<(9/c-8)/10$, there exist infinitely many primes of the form $p=\left[n^c\right]$ with $n\in \mathbb{N}$ such that $||αp||<p^{-θ}$.

math.NT↗

Primes and polygonal numbers

A linear combination $aT_r(m)+bT_s(n)$ of an \mbox{$r$-gonal} number $T_r(m)$ and an $s$-gonal number $T_s(n)$ with mutually coprime positive integer coefficients $a$ and $b$ produces infinitely many primes as $m$ and~$n$ varies over the natural numbers, whereas the sum of the reciprocals of such primes converges unless $T_r(m)=m^2$ and $T_s(n)=n^2$. For each pair of coprime positive integers $a$ and $b$, there are arbitrary long arithmetic progressions among the primes of the form $am^2+bn^2$.

math.NT↗

Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation

Complex neural networks require substantial memory to store a large number of synaptic weights. This work introduces WINGs (Automatic Weight Generator for Secure and Storage-Efficient Deep Learning Models), a novel framework that dynamically generates layer weights in a fully connected neural network (FC) and compresses the weights in convolutional neural networks (CNNs) during inference, significantly reducing memory requirements without sacrificing accuracy. WINGs framework uses principal component analysis (PCA) for dimensionality reduction and lightweight support vector regression (SVR) models to predict layer weights in the FC networks, removing the need for storing full-weight matrices and achieving substantial memory savings. It also preferentially compresses the weights in low-sensitivity layers of CNNs using PCA and SVR with sensitivity analysis. The sensitivity-aware design also offers an added level of security, as any bit-flip attack with weights in compressed layers has an amplified and readily detectable effect on accuracy. WINGs achieves 53x compression for the FC layers and 28x for AlexNet with MNIST dataset, and 18x for Alexnet with CIFAR-10 dataset with 1-2% accuracy loss. This significant reduction in memory results in higher throughput and lower energy for DNN inference, making it attractive for resource-constrained edge applications.

cs.LG↗

Runtime Detection of Adversarial Attacks in AI Accelerators Using Performance Counters

Rapid adoption of AI technologies raises several major security concerns, including the risks of adversarial perturbations, which threaten the confidentiality and integrity of AI applications. Protecting AI hardware from misuse and diverse security threats is a challenging task. To address this challenge, we propose SAMURAI, a novel framework for safeguarding against malicious usage of AI hardware and its resilience to attacks. SAMURAI introduces an AI Performance Counter (APC) for tracking dynamic behavior of an AI model coupled with an on-chip Machine Learning (ML) analysis engine, known as TANTO (Trained Anomaly Inspection Through Trace Observation). APC records the runtime profile of the low-level hardware events of different AI operations. Subsequently, the summary information recorded by the APC is processed by TANTO to efficiently identify potential security breaches and ensure secure, responsible use of AI. SAMURAI enables real-time detection of security threats and misuse without relying on traditional software-based solutions that require model integration. Experimental results demonstrate that SAMURAI achieves up to 97% accuracy in detecting adversarial attacks with moderate overhead on various AI models, significantly outperforming conventional software-based approaches. It enhances security and regulatory compliance, providing a comprehensive solution for safeguarding AI against emergent threats.

cs.CR↗

Primes in Tuples of Linear Forms in Number Fields and Function Fields

Following the work of Castillo-Hall-Oliver-Pollack-Thompson who extended Maynard-Tao theorem on admissible tuples to number fields and function fields for tuples with monic linear forms, here we obtain the Maynard-Tao theorem for admissible tuples of linear forms with arbitrary leading coefficients in number fields and function fields. Also, we provide some applications of our results.

math.NT↗

Representation of even Gaussian integer à la Chen

In this article, we represent an even Gaussian integer with sufficiently large norm as a sum of a Gaussian prime and a Gaussian integer with at most two Gaussian prime factors akin to Chen in the rational case.

math.NT↗