arXiv subjects

Vyas Sekar

Publications and source records attributed to Vyas Sekar.

At least 19 recordsLinked to original sources

arXiv2026

ASAP: Reimagining the Data Lifecycle using Application Semantic-Aware Processing

Across many domains (e.g., observability, networking, security), data processing pipelines face what we refer to as the CSP problem: achieving low Cost at large Scale, while maintaining high Performance. In response, we see several efforts to tackle CSP in various stages of the Collect-Transmit-Store-Analyze data lifecycle; such as approximate query processing in databases or sketches in network routers. Our work is driven by the simple insight: "seeing the forest for the trees". These proposed solutions (e.g., AQP, sketching, compression, rollups) addressing CSP share a common property - they exploit semantic-preserving opportunities to support application needs. In this paper, we make a case for ASAP, a paradigm that makes Application Semantic-Aware Processing (ASAP) a first-class design principle in data processing pipelines. We argue that by taking a unified view across ASAP primitives developed in different domains, across the entire data lifecycle, we can unlock new opportunities to tackle the CSP problem. In particular, we can: (i) enable novel cross-lifecycle optimizations such as analytics run directly on sketches computed at the source; (ii) leverage primitives developed in other application domains; and (iii) enable widespread adoption of these powerful techniques. We discuss research challenges in socializing the benefits of the ASAP paradigm, and show preliminary evidence that adopting ASAP can yield up to 3 orders of magnitude improvements in the CSP tradeoff for many application domains.

cs.DB↗

arXiv2026

TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data

Synthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows. Modern generative models are evaluated by their statistical similarity, correlation structure, privacy, and downstream machine-learning utility. However, such evaluations leave a gap: they rarely test the structure that matters for analytical queries. We present TabQueryBench, a query-centric benchmark that uses SQL-shaped analytical queries as structural assessors for synthetic data fidelity. It provides an extensible foundation for query-centric synthetic-data evaluation. From 12 public sources of analytical queries, TabQueryBench taxonomizes recurring cross-domain logic into 44 reusable query templates and grounds them to each dataset via a policy-guided template-to-SQL pipeline. This makes queries schema-aware while preserving comparability across generative models. Across 49 datasets and 11 generative models, it activates 10-12 templates per dataset, producing more than 100 executable SQL queries per dataset. Our systematic experiments show five main patterns. First, current tabular generative models can have good distance-based fidelity, but they still fall short on query-centric fidelity: RealTabFormer achieves the highest query-centric fidelity, but it only reaches 0.75 +/- 0.15 (REAL data score is 1.00). Second, tabular generative models struggle with very high-cardinality discrete support. Third, SOTA generative models preserve good global conditional query-centric fidelity, but fail more on local queries. Fourth, tail fidelity deteriorates as queries move toward the extreme tail; even the best model recovers only about 40.7% of real rare values. Finally, there is a fidelity-cost tradeoff in tabular generation: BayesNet offers the strongest tradeoff, with slightly lower query-centric fidelity but much lower generation cost.

cs.DB↗

arXiv2026

AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems

The computer systems community has recently seen growing interest in AI-driven system evolution, where AI agents iteratively rewrite systems. Frameworks such as AdaEvolve and Engram report 12-60% score improvements over human-designed algorithms. While these results are promising, there are practical concerns if these AI-evolved programs can perform worse on unseen workloads and exhibit scalability regressions. Given the speed and scale of AI-generated code, we need automated mechanisms to uncover such identify hidden weaknesses in AI-evolved systems programs. To this end, we develop AIChilles that takes as input a baseline program $P$ and an AI-evolved program $P'$, AIChilles searches for valid workloads where $P'$ regresses relative to $P$ in correctness, runtime, memory usage, or output quality. To tackle the diversity in system applications, weakness types and potential bugs, AIChilles combines deterministic workload-parameter extraction, agent-based constraint inference, differential oracles, and code-frequency coverage to discover diverse failures. Across five system applications and 30 AI-evolved programs, AIChilles finds 49 distinct hidden weaknesses. We also show that explicitly including AIChilles in the AI-driven development lifecycle can mitigate several of these weaknesses.

cs.AI↗

arXiv2026

Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel

Across many domains (e.g., IoT, observability, telecommunications, cybersecurity), there is an emerging adoption of conversational data analysis agents that enable users to "talk to your data" to extract insights. Such data analysis agents operate on timeseries data models; e.g., measurements from sensors or events monitoring user clicks and actions in product analytics. We evaluate 6 popular data analysis agents (both open-source and proprietary) on domain-specific data and query types, and find that they fail on stateful and incident-specific queries. We observe two key expressivity gaps in existing evals: domain-customized datasets and domain-specific query types. To enable practitioners in such domains to generate customized and expressive evals for such timeseries data agents, we present AgentFuel. AgentFuel helps domain experts quickly create customized evals to perform end-to-end functional tests. We show that AgentFuel's benchmarks expose key directions for improvement in existing data agent frameworks. We also present anecdotal evidence that using AgentFuel can improve agent performance (e.g., with GEPA). AgentFuel benchmarks are available at https://huggingface.co/datasets/RockfishData/TimeSeriesAgentEvals.

cs.AI↗

arXiv2026

AHA: Scalable Alternative History Analysis for Operational Timeseries Applications

Many operational systems collect high-dimensional timeseries data about users/systems on key performance metrics. For instance, ISPs, content distribution networks, and video delivery services collect quality of experience metrics for user sessions associated with metadata (e.g., location, device, ISP). Over such historical data, operators and data analysts often need to run retrospective analysis; e.g., analyze anomaly detection algorithms, experiment with different configurations for alerts, evaluate new algorithms, and so on. We refer to this class of workloads as alternative history analysis for operational datasets. We show that in such settings, traditional data processing solutions (e.g., data warehouses, sampling, sketching, big-data systems) either pose high operational costs or do not guarantee accurate replay. We design and implement a system, called AHA (Alternative History Analytics), that overcomes both challenges to provide cost efficiency and fidelity for high-dimensional data. The design of AHA is based on analytical and empirical insights about such workloads: 1) the decomposability of underlying statistics; 2) sparsity in terms of active number of subpopulations over attribute-value combinations; and 3) efficiency structure of aggregation operations in modern analytics databases. Using multiple real-world datasets and as well as case-studies on production pipelines at a large video analytics company, we show that AHA provides 100% accuracy for a broad range of downstream tasks and up to 85x lower total cost of ownership (i.e., compute + storage) compared to conventional methods.

cs.DB↗

arXiv2025

Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks

Security operators use red teams to simulate real attackers and proactively find defense gaps. In realistic enterprise settings, this involves executing multi-host network attacks spanning many "stepping stone" hosts. Unfortunately, red teams are expensive and entail significant expertise and effort. Given the promise of LLMs in CTF challenges, we first analyze if LLMs can autonomously execute multi-host red team exercises. We find that state-of-the-art LLM-assisted offense systems (e.g., PentestGPT, CyberSecEval3) with leading LLMs (e.g., Sonnet 4, Gemini 2.5 Pro) are unable to do so. Building on our observations in understanding the failure modes of state-of-the-art systems, we argue the need to improve the abstractions and interfaces for LLM-assisted red teaming. Based on this insight, we present the design and implementation of Incalmo, an LLM-assisted system for autonomously red teaming multi-host networks. Incalmo uses LLMs to plan red team exercises in terms of high-level declarative tasks that are executed by domain-specific task agents. Incalmo also uses auxiliary services to manage context and acquired assets. For our evaluation, we develop MHBench, a novel multi-host attack benchmark with 40 realistic emulated networks (from 22 to 50 hosts). We find that Incalmo successfully acquires critical assets (i.e., key hosts or data) in 37 out of 40 MHBench environments. In contrast, state-of-the-art LLM-assisted systems succeed in only 3 out of 40 environments. We show that Incalmo is efficient-successful attacks took 12-54 minutes and cost <$15 in LLM credits.

cs.CR↗

arXiv2025

Cyber-Resilient System Identification for Power Grid through Bayesian Integration

Power grids increasingly need real-time situational awareness under the ever-evolving cyberthreat landscape. Advances in snapshot-based system identification approaches have enabled accurately estimating states and topology from a snapshot of measurement data, under random bad data and topology errors. However, modern interactive, targeted false data can stay undetectable to these methods, and significantly compromise estimation accuracy. This work advances system identification that combines snapshot-based method with time-series model via Bayesian Integration, to advance cyber resiliency against both random and targeted false data. Using a distance-based time-series model, this work can leverage historical data of different distributions induced by changes in grid topology and other settings. The normal system behavior captured from historical data is integrated into system identification through a Bayesian treatment, to make solutions robust to targeted false data. We experiment on mixed random anomalies (bad data, topology error) and targeted false data injection attack (FDIA) to demonstrate our method's 1) cyber resilience: achieving over 70% reduction in estimation error under FDIA; 2) anomalous data identification: being able to alarm and locate anomalous data; 3) almost linear scalability: achieving comparable speed with the snapshot-based baseline, both taking <1min per time tick on the large 2,383-bus system using a laptop CPU.

eess.SY↗

arXiv2025

Perry: A High-level Framework for Accelerating Cyber Deception Experimentation

Cyber deception aims to distract, delay, and detect network attackers with fake assets such as honeypots, decoy credentials, or decoy files. However, today, it is difficult for operators to experiment, explore, and evaluate deception approaches. Existing tools and platforms have non-portable and complex implementations that are difficult to modify and extend. We address this pain point by introducing Perry, a high-level framework that accelerates the design and exploration of deception what-if scenarios. Perry has two components: a high-level abstraction layer for security operators to specify attackers and deception strategies, and an experimentation module to run these attackers and defenders in realistic emulated networks. To translate these high-level specifications we design four key modules for Perry: 1) an action planner that translates high-level actions into low-level implementations, 2) an observability module to translate low-level telemetry into high-level observations, 3) an environment state service that enables environment agnostic strategies, and 4) an attack graph service to reason about how attackers could explore an environment. We illustrate that Perry's abstractions reduce the implementation effort of exploring a wide variety of deception defenses, attackers, and environments. We demonstrate the value of Perry by emulating 55 unique deception what-if scenarios and illustrate how these experiments enable operators to shed light on subtle tradeoffs.

cs.CR↗

arXiv2025

SPIDER: Fuzzing for Stateful Performance Issues in the ONOS Software-Defined Network Controller

Performance issues in software-defined network (SDN) controllers can have serious impacts on the performance and availability of networks. In this paper, we consider a special class of SDN vulnerabilities called stateful performance issues (SPIs), where a sequence of initial input messages drives the controller into a state such that its performance degrades pathologically when processing subsequent messages. Uncovering SPIs in large complex software such as the widely used ONOS SDN controller is challenging because of the large state space of input sequences and the complex software architecture of inter-dependent network services. We present SPIDER, a practical fuzzing framework for identifying SPIs in this setting. The key contribution in our work is to leverage the event-driven modular software architecture of the SDN controller to (a) separately target each network service for SPIs and (b) use static analysis to identify all services whose event handlers can affect the state of the target service directly or indirectly. SPIDER implements this novel dependency-aware modular performance fuzzing approach for 157 network services in ONOS and successfully identifies 10 new performance issues. We present an evaluation of SPIDER against prior work, a sensitivity analysis of design decisions, and case studies of two uncovered SPIs.

cs.CR↗

arXiv2024

Network Function Capacity Reconnaissance by Remote Adversaries

There is anecdotal evidence that attackers use reconnaissance to learn the capacity of their victims before DDoS attacks to maximize their impact. The first step to mitigate capacity reconnaissance attacks is to understand their feasibility. However, the feasibility of capacity reconnaissance in network functions (NFs) (e.g., firewalls, NATs) is unknown. To this end, we formulate the problem of network function capacity reconnaissance (NFCR) and explore the feasibility of inferring the processing capacity of an NF while avoiding detection. We identify key factors that make NFCR challenging and analyze how these factors affect accuracy (measured as a divergence from ground truth) and stealthiness (measured in packets sent). We propose a flexible tool, NFTY, that performs NFCR and we evaluate two practical NFTY configurations to showcase the stealthiness vs. accuracy tradeoffs. We evaluate these strategies in controlled, Internet and/or cloud settings with commercial NFs. NFTY can accurately estimate the capacity of different NF deployments within 10% error in the controlled experiments and the Internet, and within 7% error for a commercial NF deployed in the cloud (AWS). Moreover, NFTY outperforms link-bandwidth estimation baselines by up to 30x.

cs.NI↗

arXiv2023

Summary Statistic Privacy in Data Sharing

We study a setting where a data holder wishes to share data with a receiver, without revealing certain summary statistics of the data distribution (e.g., mean, standard deviation). It achieves this by passing the data through a randomization mechanism. We propose summary statistic privacy, a metric for quantifying the privacy risk of such a mechanism based on the worst-case probability of an adversary guessing the distributional secret within some threshold. Defining distortion as a worst-case Wasserstein-1 distance between the real and released data, we prove lower bounds on the tradeoff between privacy and distortion. We then propose a class of quantization mechanisms that can be adapted to different data distributions. We show that the quantization mechanism's privacy-distortion tradeoff matches our lower bounds under certain regimes, up to small constant factors. Finally, we demonstrate on real-world datasets that the proposed quantization mechanisms achieve better privacy-distortion tradeoffs than alternative privacy mechanisms.

cs.CR↗

arXiv2023

CANE: A Cascade-Control Approach for Network-Assisted Video QoE Management

Prior efforts have shown that network-assisted schemes can improve the Quality-of-Experience (QoE) and QoE fairness when multiple video players compete for bandwidth. However, realizing network-assisted schemes in practice is challenging, as: i) the network has limited visibility into the client players' internal state and actions; ii) players' actions may nullify or negate the network's actions; and iii) the players' objectives might be conflicting. To address these challenges, we formulate network-assisted QoE optimization through a cascade control abstraction. This informs the design of CANE, a practical network-assisted QoE framework. CANE uses machine learning techniques to approximate each player's behavior as a black-box model and model predictive control to achieve a near-optimal solution. We evaluate CANE through realistic simulations and show that CANE improves multiplayer QoE fairness by ~50% compared to pure client-side adaptive bitrate algorithms and by ~20% compared to uniform traffic shaping.

math.OC↗

arXiv2022

Rethinking Data-driven Networking with Foundation Models: Challenges and Opportunities

Foundational models have caused a paradigm shift in the way artificial intelligence (AI) systems are built. They have had a major impact in natural language processing (NLP), and several other domains, not only reducing the amount of required labeled data or even eliminating the need for it, but also significantly improving performance on a wide range of tasks. We argue foundation models can have a similar profound impact on network traffic analysis, and management. More specifically, we show that network data shares several of the properties that are behind the success of foundational models in linguistics. For example, network data contains rich semantic content, and several of the networking tasks (e.g., traffic classification, generation of protocol implementations from specification text, anomaly detection) can find similar counterparts in NLP (e.g., sentiment analysis, translation from natural language to code, out-of-distribution). However, network settings also present unique characteristics and challenges that must be overcome. Our contribution is in highlighting the opportunities and challenges at the intersection of foundation models and networking.

cs.NI↗

arXiv2022

Enabling Efficient and General Subpopulation Analytics in Multidimensional Data Streams

Today's large-scale services (e.g., video streaming platforms, data centers, sensor grids) need diverse real-time summary statistics across multiple subpopulations of multidimensional datasets. However, state-of-the-art frameworks do not offer general and accurate analytics in real time at reasonable costs. The root cause is the combinatorial explosion of data subpopulations and the diversity of summary statistics we need to monitor simultaneously. We present Hydra, an efficient framework for multidimensional analytics that presents a novel combination of using a ``sketch of sketches'' to avoid the overhead of monitoring exponentially-many subpopulations and universal sketching to ensure accurate estimates for multiple statistics. We build Hydra as an Apache Spark plugin and address practical system challenges to minimize overheads at scale. Across multiple real-world and synthetic multidimensional datasets, we show that Hydra can achieve robust error bounds and is an order of magnitude more efficient in terms of operational cost and memory footprint than existing frameworks (e.g., Spark, Druid) while ensuring interactive estimation times.

cs.DB↗

arXiv2022

On the Privacy Properties of GAN-generated Samples

The privacy implications of generative adversarial networks (GANs) are a topic of great interest, leading to several recent algorithms for training GANs with privacy guarantees. By drawing connections to the generalization properties of GANs, we prove that under some assumptions, GAN-generated samples inherently satisfy some (weak) privacy guarantees. First, we show that if a GAN is trained on m samples and used to generate n samples, the generated samples are (epsilon, delta)-differentially-private for (epsilon, delta) pairs where delta scales as O(n/m). We show that under some special conditions, this upper bound is tight. Next, we study the robustness of GAN-generated samples to membership inference attacks. We model membership inference as a hypothesis test in which the adversary must determine whether a given sample was drawn from the training dataset or from the underlying data distribution. We show that this adversary can achieve an area under the ROC curve that scales no better than O(m^{-1/4}).

cs.LG↗

arXiv2022

RareGAN: Generating Samples for Rare Classes

We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget. This problem is motivated from practical applications in domains including security (e.g., synthesizing packets for DNS amplification attacks), systems and networking (e.g., synthesizing workloads that trigger high resource usage), and machine learning (e.g., generating images from a rare class). Existing approaches are unsuitable, either requiring fully-labeled datasets or sacrificing the fidelity of the rare class for that of the common classes. We propose RareGAN, a novel synthesis of three key ideas: (1) extending conditional GANs to use labelled and unlabelled data for better generalization; (2) an active learning approach that requests the most useful labels; and (3) a weighted loss function to favor learning the rare class. We show that RareGAN achieves a better fidelity-diversity tradeoff on the rare class than prior work across different applications, budgets, rare class fractions, GAN losses, and architectures.

cs.LG↗

arXiv2021

A Roadmap for Enabling a Future-Proof In-Network Computing Data Plane Ecosystem

As the vision of in-network computing becomes more mature, we see two parallel evolutionary trends. First, we see the evolution of richer, more demanding applications that require capabilities beyond programmable switching ASICs. Second, we see the evolution of diverse data plane technologies with many other future capabilities on the horizon. While some point solutions exist to tackle the intersection of these trends, we see several ecosystem-level disconnects today; e.g., the need to refactor applications for new data planes, lack of systematic guidelines to inform the development of future data plane capabilities, and lack of holistic runtime frameworks for network operators. In this paper, we use a simple-yet-instructive emerging application-data plane combination to highlight these disconnects. Drawing on these lessons, we sketch a high-level roadmap and guidelines for the community to tackle these to create a more thriving "future-proof" data plane ecosystem.

cs.NI↗

arXiv2021

Why Spectral Normalization Stabilizes GANs: Analysis and Improvements

Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs). However, there is currently limited understanding of why SN is effective. In this work, we show that SN controls two important failure modes of GAN training: exploding and vanishing gradients. Our proofs illustrate a (perhaps unintentional) connection with the successful LeCun initialization. This connection helps to explain why the most popular implementation of SN for GANs requires no hyper-parameter tuning, whereas stricter implementations of SN have poor empirical performance out-of-the-box. Unlike LeCun initialization which only controls gradient vanishing at the beginning of training, SN preserves this property throughout training. Building on this theoretical understanding, we propose a new spectral normalization technique: Bidirectional Scaled Spectral Normalization (BSSN), which incorporates insights from later improvements to LeCun initialization: Xavier initialization and Kaiming initialization. Theoretically, we show that BSSN gives better gradient control than SN. Empirically, we demonstrate that it outperforms SN in sample quality and training stability on several benchmark datasets.

cs.LG↗