arXiv subjects

Kunal Jain

Publications and source records attributed to Kunal Jain.

8 recordsLinked to original sources

arXiv2026

CloakLM: Obfuscating GPU Memory Layout to Mitigate Model Ex-filtration for Serving

Large foundation models deployed on third-party and shared accelerator infrastructure face a practical risk of model exfiltration that existing defenses do not fully address. In common serving deployments, model providers control the VM or bare-metal serving stack but not the surrounding hardware substrate. The host to GPU interconnect, accelerator fabric, and neighboring infrastructure components remain outside the tenant's trust boundary and have been shown to be exploitable. Hermes demonstrates lossless DNN reconstruction from passive PCIe observation, while TunnelS exfiltrates HBM contents at high throughput via driver-level access without disrupting inference. Co-tenant VMs can further access memory-mapped interfaces or misconfigured RDMA regions without physical co-location. These attacks exploit a common property of ML systems: model weights are stored in large, contiguous, and repeatedly accessed memory regions, making intercepted PCIe transfers and HBM dumps rich enough to reveal model structure and parameters. We present CloakLM, a software-only memory-obfuscation framework that removes this structural regularity without changing the inference stack's logical view of memory. CloakLM combines three mechanisms: PCIe traffic shaping, inter- and intra-layer weight shuffling, and physical HBM page remapping. Authorized execution retains a valid virtual memory layout with negligible overhead, while unauthorized observers see fragmented and semantically incoherent state. CloakLM integrates with vLLM and PyTorch, requires no hardware changes, and complements confidential computing. Evaluation on distributed inference workloads using LLaMA and Qwen models shows near-native performance while significantly increasing resistance to PCIe snooping and HBM dump attacks, making inference-time model exfiltration substantially less practical.

cs.OS↗

arXiv2026

Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family

Recent research has shown that contrastive vision-language models such as CLIP often lack fine-grained understanding of visual content. While a growing body of work has sought to address this limitation, we identify a distinct failure mode in the CLIP family, which we term center bias, that persists even in recent model variants. Specifically, CLIP tends to disproportionately focus on the central region of an image, overlooking important objects located near the boundaries. This limitation is fundamental as failure to recognize relevant objects makes it difficult to perform any sophisticated tasks that depend on those objects. To understand the underlying causes of the limitation, we conduct analyses from both representation and attention perspectives. Using interpretability methods, i.e., embedding decomposition and attention map analysis, we find that relevant concepts especially those associated with off-center objects vanish from the model's embedding in the final representation due to information loss during the aggregation of visual embeddings, particularly the reliance on pooling mechanisms. Finally, we show that this bias can be alleviated with training-free strategies such as visual prompting and attention redistribution by redirecting models' attention to off-center regions.

cs.CV↗

arXiv2025

SageServe: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-Scaling

Global cloud service providers handle inference workloads for Large Language Models (LLMs) that span latency-sensitive (e.g., chatbots) and insensitive (e.g., report writing) tasks, resulting in diverse and often conflicting Service Level Agreement (SLA) requirements. Managing such mixed workloads is challenging due to the complexity of the inference serving stack, which encompasses multiple models, GPU hardware, and global data centers. Existing solutions often silo such fast and slow tasks onto separate GPU resource pools with different SLAs, but this leads to significant under-utilization of expensive accelerators due to load mismatch. In this article, we characterize the LLM serving workloads at Microsoft Office 365, one of the largest users of LLMs within Microsoft Azure cloud with over 10 million requests per day, and highlight key observations across workloads in different data center regions and across time. This is one of the first such public studies of Internet-scale LLM workloads. We use these insights to propose SageServe, a comprehensive LLM serving framework that dynamically adapts to workload demands using multi-timescale control knobs. It combines short-term request routing to data centers with long-term scaling of GPU VMs and model placement with higher lead times, and co-optimizes the routing and resource allocation problem using a traffic forecast model and an Integer Linear Programming (ILP) solution. We evaluate SageServe through real runs and realistic simulations on 10 million production requests across three regions and four open-source models. We achieve up to 25% savings in GPU-hours compared to the current baseline deployment and reduce GPU-hour wastage due to inefficient auto-scaling by 80%, resulting in a potential monthly cost savings of up to $2.5 million, while maintaining tail latency and meeting SLAs.

cs.DC↗

arXiv2025

Compact Neural TTS Voices for Accessibility

Contemporary text-to-speech solutions for accessibility applications can typically be classified into two categories: (i) device-based statistical parametric speech synthesis (SPSS) or unit selection (USEL) and (ii) cloud-based neural TTS. SPSS and USEL offer low latency and low disk footprint at the expense of naturalness and audio quality. Cloud-based neural TTS systems provide significantly better audio quality and naturalness but regress in terms of latency and responsiveness, rendering these impractical for real-world applications. More recently, neural TTS models were made deployable to run on handheld devices. Nevertheless, latency remains higher than SPSS and USEL, while disk footprint prohibits pre-installation for multiple voices at once. In this work, we describe a high-quality compact neural TTS system achieving latency on the order of 15 ms with low disk footprint. The proposed solution is capable of running on low-power devices.

cs.SD↗

arXiv2024

Ensuring Fair LLM Serving Amid Diverse Applications

In a multi-tenant large language model (LLM) serving platform hosting diverse applications, some users may submit an excessive number of requests, causing the service to become unavailable to other users and creating unfairness. Existing fairness approaches do not account for variations in token lengths across applications and multiple LLM calls, making them unsuitable for such platforms. To address the fairness challenge, this paper analyzes millions of requests from thousands of users on MS CoPilot, a real-world multi-tenant LLM platform hosted by Microsoft. Our analysis confirms the inadequacy of existing methods and guides the development of FairServe, a system that ensures fair LLM access across diverse applications. FairServe proposes application-characteristic aware request throttling coupled with a weighted service counter based scheduling technique to curb abusive behavior and ensure fairness. Our experimental results on real-world traces demonstrate FairServe's superior performance compared to the state-of-the-art method in ensuring fairness. We are actively working on deploying our system in production, expecting to benefit millions of customers world-wide.

cs.LG↗

arXiv2024

Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Load Balancing

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster. However existing scheduling algorithms treat LLM workloads as monolithic jobs without considering the distinct characteristics of the two phases in each workload. This leads to sub-optimal scheduling and increased response latency. In this work, we start by characterizing factors affecting the response latency during LLM inference serving. We establish that better load balancing of inference requests across the available LLM instances can improve the end-to-end latency to a larger extent than merely focusing on optimizing the instance-level scheduler. Motivated by our findings, we propose a heuristic-guided reinforcement learning-based intelligent router for data-driven and workload-aware scheduling. Our router schedules queries across LLM instances by leveraging a trainable response-length predictor, and a novel formulation for estimating the impact of mixing different workloads and achieves over 11% lower end-to-end latency than existing approaches on a mix of public datasets and 7.8% lower end-to-end latency on real workload data with diverse input and output trends from Cloud Provider X. Additionally, the proposed framework can also serve as a standard for benchmarking different LLM inference schedulers since it provides the best latency for a given model, hardware, and instance-level scheduler combination.

cs.DC↗

arXiv2023

Bayesian Optimization for Function Compositions with Applications to Dynamic Pricing

Bayesian Optimization (BO) is used to find the global optima of black box functions. In this work, we propose a practical BO method of function compositions where the form of the composition is known but the constituent functions are expensive to evaluate. By assuming an independent Gaussian process (GP) model for each of the constituent black-box function, we propose Expected Improvement (EI) and Upper Confidence Bound (UCB) based BO algorithms and demonstrate their ability to outperform not just vanilla BO but also the current state-of-art algorithms. We demonstrate a novel application of the proposed methods to dynamic pricing in revenue management when the underlying demand function is expensive to evaluate.

cs.LG↗

arXiv2012

Classification of Flames in Computer Mediated Communications

Computer Mediated Communication (CMC) has brought about a revolution in the way the world communicates with each other. With the increasing number of people, interacting through the internet and the rise of new platforms and technologies has brought together the people from different social, cultural and geographical backgrounds to present their thoughts, ideas and opinions on topics of their interest. CMC has, in some cases, gave users more freedom to express themselves as compared to Face-to-face communication. This has also led to rise in the use of hostile and aggressive language and terminologies uninhibitedly. Since such use of language is detrimental to the discussion process and affects the audience and individuals negatively, efforts are being taken to control them. The research sees the need to understand the concept of flaming and hence attempts to classify them in order to give a better understanding of it. The classification is done on the basis of type of flame content being presented and the Style in which they are presented.

cs.SI↗