arXiv subjects

Matthew Caesar

Publications and source records attributed to Matthew Caesar.

At least 19 recordsLinked to original sources

arXiv2026

Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment

Autonomous Unmanned Aerial Vehicle (UAV) swarms are increasingly used as rapidly deployable aerial relays and sensing platforms, yet practical deployments must operate under partial observability and intermittent peer-to-peer connectivity. We present a graph-based multi-agent reinforcement learning framework trained under centralized training with decentralized execution (CTDE): a centralized critic and global state are available only during training, while each UAV executes a shared policy using local observations and messages from nearby neighbors. Under restricted communication, neighbor relations are induced by an SNR-threshold connectivity graph. Our architecture encodes local agent state and nearby entities with an agent-entity attention module and aggregates inter-UAV messages with neighbor self-attention over a signal-quality-limited communication graph defined by a channel model. We evaluate the framework on a cooperative relay-deployment task, DroneConnect. Experimental results show that the proposed method achieves an approximately 12% increase in target coverage over MAPPO under restricted communication and partial observability, while remaining competitive with a mixed-integer linear programming (MILP)-based offline upper bound with full node observability.

cs.MA↗

arXiv2025

SIFT-Graph: Benchmarking Multimodal Defense Against Image Adversarial Attacks With Robust Feature Graph

Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense strategies typically operate within this fragile pixel domain, lacking mechanisms to incorporate inherently robust visual features. In this work, we introduce SIFT-Graph, a multimodal defense framework that enhances the robustness of traditional vision models by aggregating structurally meaningful features extracted from raw images using both handcrafted and learned modalities. Specifically, we integrate Scale-Invariant Feature Transform keypoints with a Graph Attention Network to capture scale and rotation invariant local structures that are resilient to perturbations. These robust feature embeddings are then fused with traditional vision model, such as Vision Transformer and Convolutional Neural Network, to form a unified, structure-aware and perturbation defensive model. Preliminary results demonstrate that our method effectively improves the visual model robustness against gradient-based white box adversarial attacks, while incurring only a marginal drop in clean accuracy.

cs.CV↗

arXiv2024

Fine-grained Distributed Data Plane Verification with Intent-based Slicing

Data plane verification has grown into a powerful tool to ensure network correctness. However, existing methods with monolithic models have memory requirements tied to network sizes, and the existing method of scaling out is too limited in expressiveness to capture practical network features. In this paper, we describe Scylla, a general data plane verifier that provides fine-grained scale-out without the need for a monolithic network model. Scylla creates models for what we call intent-based slices, each of which is constructed at the rule-level granularity with only enough to verify a given set of intents. The sliced models are retained and incrementally updated in memory across a distributed compute cluster in response to network updates. Our experiments show that Scylla makes the scaling problem more granular -- tied to the size of the intent-based slices rather than that of the overall network. This enables Scylla to verify large, complex networks in minimum units of work that are significantly smaller (in both memory and time) than past techniques, enabling fast scale-out verification with minimal resource requirement.

cs.NI↗

arXiv2021

Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras

Increasing demand for meat products combined with farm labor shortages has resulted in a need to develop new real-time solutions to monitor animals effectively. Significant progress has been made in continuously locating individual pigs using tracking-by-detection methods. However, these methods fail for oblong pens because a single fixed camera does not cover the entire floor at adequate resolution. We address this problem by using multiple cameras, placed such that the visual fields of adjacent cameras overlap, and together they span the entire floor. Avoiding breaks in tracking requires inter-camera handover when a pig crosses from one camera's view into that of an adjacent camera. We identify the adjacent camera and the shared pig location on the floor at the handover time using inter-view homography. Our experiments involve two grow-finish pens, housing 16-17 pigs each, and three RGB cameras. Our algorithm first detects pigs using a deep learning-based object detection model (YOLO) and creates their local tracking IDs using a multi-object tracking algorithm (DeepSORT). We then use inter-camera shared locations to match multiple views and generate a global ID for each pig that holds throughout tracking. To evaluate our approach, we provide five two-minutes long video sequences with fully annotated global identities. We track pigs in a single camera view with a Multi-Object Tracking Accuracy and Precision of 65.0% and 54.3% respectively and achieve a Camera Handover Accuracy of 74.0%. We open-source our code and annotated dataset at https://github.com/AIFARMS/multi-camera-pig-tracking

cs.CV↗

arXiv2021

Vision-based Behavioral Recognition of Novelty Preference in Pigs

Behavioral scoring of research data is crucial for extracting domain-specific metrics but is bottlenecked on the ability to analyze enormous volumes of information using human labor. Deep learning is widely viewed as a key advancement to relieve this bottleneck. We identify one such domain, where deep learning can be leveraged to alleviate the process of manual scoring. Novelty preference paradigms have been widely used to study recognition memory in pigs, but analysis of these videos requires human intervention. We introduce a subset of such videos in the form of the 'Pig Novelty Preference Behavior' (PNPB) dataset that is fully annotated with pig actions and keypoints. In order to demonstrate the application of state-of-the-art action recognition models on this dataset, we compare LRCN, C3D, and TSM on the basis of various analytical metrics and discuss common pitfalls of the models. Our methods achieve an accuracy of 93% and a mean Average Precision of 96% in estimating piglet behavior. We open-source our code and annotated dataset at https://github.com/AIFARMS/NOR-behavior-recognition

cs.CV↗

arXiv2019

Plankton: Scalable network configuration verification through model checking

Network configuration verification enables operators to ensure that the network will behave as intended, prior to deployment of their configurations. Although techniques ranging from graph algorithms to SMT solvers have been proposed, scalable configuration verification with sufficient protocol support continues to be a challenge. In this paper, we show that by combining equivalence partitioning with explicit-state model checking, network configuration verification can be scaled significantly better than the state of the art, while still supporting a rich set of protocol features. We propose Plankton, which uses symbolic partitioning to manage large header spaces and efficient model checking to exhaustively explore protocol behavior. Thanks to a highly effective suite of optimizations including state hashing, partial order reduction, and policy-based pruning, Plankton successfully verifies policies in industrial-scale networks quickly and compactly, at times reaching a 10000$\times$ speedup compared to the state of the art.

cs.NI↗

arXiv2015

Exploring Ways To Mitigate Sensor-Based Smartphone Fingerprinting

Modern smartphones contain motion sensors, such as accelerometers and gyroscopes. These sensors have many useful applications; however, they can also be used to uniquely identify a phone by measuring anomalies in the signals, which are a result from manufacturing imperfections. Such measurements can be conducted surreptitiously in the browser and can be used to track users across applications, websites, and visits. We analyze techniques to mitigate such device fingerprinting either by calibrating the sensors to eliminate the signal anomalies, or by adding noise that obfuscates the anomalies. To do this, we first develop a highly accurate fingerprinting mechanism that combines multiple motion sensors and makes use of (inaudible) audio stimulation to improve detection. We then collect measurements from a large collection of smartphones and evaluate the impact of calibration and obfuscation techniques on the classifier accuracy.

cs.CR↗

arXiv2014

Defending Tor from Network Adversaries: A Case Study of Network Path Prediction

The Tor anonymity network has been shown vulnerable to traffic analysis attacks by autonomous systems and Internet exchanges, which can observe different overlay hops belonging to the same circuit. We aim to determine whether network path prediction techniques provide an accurate picture of the threat from such adversaries, and whether they can be used to avoid this threat. We perform a measurement study by running traceroutes from Tor relays to destinations around the Internet. We use the data to evaluate the accuracy of the autonomous systems and Internet exchanges that are predicted to appear on the path using state-of-the-art path inference techniques; we also consider the impact that prediction errors have on Tor security, and whether it is possible to produce a useful overestimate that does not miss important threats. Finally, we evaluate the possibility of using these predictions to actively avoid AS and IX adversaries and the challenges this creates for the design of Tor.

cs.CR↗

arXiv2014

Fingerprinting Smart Devices Through Embedded Acoustic Components

The widespread use of smart devices gives rise to both security and privacy concerns. Fingerprinting smart devices can assist in authenticating physical devices, but it can also jeopardize privacy by allowing remote identification without user awareness. We propose a novel fingerprinting approach that uses the microphones and speakers of smart phones to uniquely identify an individual device. During fabrication, subtle imperfections arise in device microphones and speakers which induce anomalies in produced and received sounds. We exploit this observation to fingerprint smart devices through playback and recording of audio samples. We use audio-metric tools to analyze and explore different acoustic features and analyze their ability to successfully fingerprint smart devices. Our experiments show that it is even possible to fingerprint devices that have the same vendor and model; we were able to accurately distinguish over 93% of all recorded audio clips from 15 different units of the same model. Our study identifies the prominent acoustic features capable of fingerprinting devices with high success rate and examines the effect of background noise and other variables on fingerprinting accuracy.

cs.CR↗

arXiv2013

Shortest Paths in Microseconds

Computing shortest paths is a fundamental primitive for several social network applications including socially-sensitive ranking, location-aware search, social auctions and social network privacy. Since these applications compute paths in response to a user query, the goal is to minimize latency while maintaining feasible memory requirements. We present ASAP, a system that achieves this goal by exploiting the structure of social networks. ASAP preprocesses a given network to compute and store a partial shortest path tree (PSPT) for each node. The PSPTs have the property that for any two nodes, each edge along the shortest path is with high probability contained in the PSPT of at least one of the nodes. We show that the structure of social networks enable the PSPT of each node to be an extremely small fraction of the entire network; hence, PSPTs can be stored efficiently and each shortest path can be computed extremely quickly. For a real network with 5 million nodes and 69 million edges, ASAP computes a shortest path for most node pairs in less than 49 microseconds per pair. ASAP, unlike any previous technique, also computes hundreds of paths (along with corresponding distances) between any node pair in less than 100 microseconds. Finally, ASAP admits efficient implementation on distributed programming frameworks like MapReduce.

cs.DC↗

arXiv2012

SWEET: Serving the Web by Exploiting Email Tunnels

Open communication over the Internet poses a serious threat to countries with repressive regimes, leading them to develop and deploy censorship mechanisms within their networks. Unfortunately, existing censorship circumvention systems do not provide high availability guarantees to their users, as censors can identify, hence disrupt, the traffic belonging to these systems using today's advanced censorship technologies. In this paper we propose SWEET, a highly available censorship-resistant infrastructure. SWEET works by encapsulating a censored user's traffic to a proxy server inside email messages that are carried over by public email service providers, like Gmail and Yahoo Mail. As the operation of SWEET is not bound to specific email providers we argue that a censor will need to block all email communications in order to disrupt SWEET, which is infeasible as email constitutes an important part of today's Internet. Through experiments with a prototype of our system we find that SWEET's performance is sufficient for web traffic. In particular, regular websites are downloaded within couple of seconds.

cs.CR↗

arXiv2012

Mirage: Towards Deployable DDoS Defense for Web Applications

Distributed Denial of Service (DDoS) attacks form a serious threat to the security of Internet services. However, despite over a decade of research, and the existence of several proposals to address this problem, there has been little progress to date on actual adoption. We present Mirage, a protocol that achieves comparable performance to other DDoS mitigation schemes while providing benefits when deployed only in the server's local network and its upstream ISP, where local business objectives may incentivize deployment. Mirage does not require source end hosts to install any software to access Mirage protected websites. Unlike previous proposals, Mirage only requires functionality from routers that is already deployed in today's routers, though this functionality may need to be scaled depending on the point of deployment. Our approach is that end hosts can thwart the attackers by employing the principle of a moving target: end hosts in our architecture periodically change IP addresses to keep the attackers guessing. Knowledge of an active IP address of the destination end host can act as an implicit authorization to send data. We evaluate Mirage using theoretical analysis, simulations and a prototype implementation on PlanetLab. We find that our design provides a first step towards a deployable, yet effective DDoS defense.

cs.NI↗

arXiv2012

Finishing Flows Quickly with Preemptive Scheduling

Today's data centers face extreme challenges in providing low latency. However, fair sharing, a principle commonly adopted in current congestion control protocols, is far from optimal for satisfying latency requirements. We propose Preemptive Distributed Quick (PDQ) flow scheduling, a protocol designed to complete flows quickly and meet flow deadlines. PDQ enables flow preemption to approximate a range of scheduling disciplines. For example, PDQ can emulate a shortest job first algorithm to give priority to the short flows by pausing the contending flows. PDQ borrows ideas from centralized scheduling disciplines and implements them in a fully distributed manner, making it scalable to today's data centers. Further, we develop a multipath version of PDQ to exploit path diversity. Through extensive packet-level and flow-level simulation, we demonstrate that PDQ significantly outperforms TCP, RCP and D3 in data center environments. We further show that PDQ is stable, resilient to packet loss, and preserves nearly all its performance gains even given inaccurate flow information.

cs.NI↗

arXiv2012

Shortest Paths in Less Than a Millisecond

We consider the problem of answering point-to-point shortest path queries on massive social networks. The goal is to answer queries within tens of milliseconds while minimizing the memory requirements. We present a technique that achieves this goal for an extremely large fraction of path queries by exploiting the structure of the social networks. Using evaluations on real-world datasets, we argue that our technique offers a unique trade-off between latency, memory and accuracy. For instance, for the LiveJournal social network (roughly 5 million nodes and 69 million edges), our technique can answer 99.9% of the queries in less than a millisecond. In comparison to storing all pair shortest paths, our technique requires at least 550x less memory; the average query time is roughly 365 microseconds --- 430x faster than the state-of-the-art shortest path algorithm. Furthermore, the relative performance of our technique improves with the size (and density) of the network. For the Orkut social network (3 million nodes and 220 million edges), for instance, our technique is roughly 2588x faster than the state-of-the-art algorithm for computing shortest paths.

cs.SI↗

arXiv2012

Tiresias: Online Anomaly Detection for Hierarchical Operational Network Data

Operational network data, management data such as customer care call logs and equipment system logs, is a very important source of information for network operators to detect problems in their networks. Unfortunately, there is lack of efficient tools to automatically track and detect anomalous events on operational data, causing ISP operators to rely on manual inspection of this data. While anomaly detection has been widely studied in the context of network data, operational data presents several new challenges, including the volatility and sparseness of data, and the need to perform fast detection (complicating application of schemes that require offline processing or large/stable data sets to converge). To address these challenges, we propose Tiresias, an automated approach to locating anomalous events on hierarchical operational data. Tiresias leverages the hierarchical structure of operational data to identify high-impact aggregates (e.g., locations in the network, failure modes) likely to be associated with anomalous events. To accommodate different kinds of operational network data, Tiresias consists of an online detection algorithm with low time and space complexity, while preserving high detection accuracy. We present results from two case studies using operational data collected at a large commercial IP network operated by a Tier-1 ISP: customer care call logs and set-top box crash logs. By comparing with a reference set verified by the ISP's operational group, we validate that Tiresias can achieve >94% accuracy in locating anomalies. Tiresias also discovered several previously unknown anomalies in the ISP's customer care cases, demonstrating its effectiveness.

cs.NI↗

arXiv2012

SybilControl: Practical Sybil Defense with Computational Puzzles

Many distributed systems are subject to the Sybil attack, where an adversary subverts system operation by emulating behavior of multiple distinct nodes. Most recent work to address this problem leverages social networks to establish trust relationships between users. However, the use of social networks is not appropriate in all systems, as they can be subverted by social engineering techniques, require nodes in a P2P network to maintain and be aware of social network information, and may require overly optimistic assumptions about the fast-mixing nature of social links. This paper explores an alternate approach. We present SybilControl, a novel, decentralized scheme for controlling the extent of Sybil attacks. SybilControl is an admission control mechanism for nodes in a distributed system that requires them to periodically solve computational puzzles. SybilControl consists of a distributed protocol to allow nodes to collectively verify the computational work of other nodes, and mechanisms to prevent the malicious influence of misbehaving nodes that do not perform the computational work. We investigate the practical issues involved with deploying SybilControl into existing DHTs, particularly with resilient lookup protocols. We evaluate SybilControl through simulations and find that SybilControl retains low overhead and latency. Additionally, even when the adversary controls 20% of the system's computational resources, SybilControl-enabled DHTs can be configured to maintain lookup performance at over 99% success rate using low communication overhead.

cs.NI↗

arXiv2012

Slick Packets

Source-controlled routing has been proposed as a way to improve flexibility of future network architectures, as well as simplifying the data plane. However, if a packet specifies its path, this precludes fast local re-routing within the network. We propose SlickPackets, a novel solution that allows packets to slip around failures by specifying alternate paths in their headers, in the form of compactly-encoded directed acyclic graphs. We show that this can be accomplished with reasonably small packet headers for real network topologies, and results in responsiveness to failures that is competitive with past approaches that require much more state within the network. Our approach thus enables fast failure response while preserving the benefits of source-controlled routing.

cs.NI↗

arXiv2011

X-Vine: Secure and Pseudonymous Routing Using Social Networks

Distributed hash tables suffer from several security and privacy vulnerabilities, including the problem of Sybil attacks. Existing social network-based solutions to mitigate the Sybil attacks in DHT routing have a high state requirement and do not provide an adequate level of privacy. For instance, such techniques require a user to reveal their social network contacts. We design X-Vine, a protection mechanism for distributed hash tables that operates entirely by communicating over social network links. As with traditional peer-to-peer systems, X-Vine provides robustness, scalability, and a platform for innovation. The use of social network links for communication helps protect participant privacy and adds a new dimension of trust absent from previous designs. X-Vine is resilient to denial of service via Sybil attacks, and in fact is the first Sybil defense that requires only a logarithmic amount of state per node, making it suitable for large-scale and dynamic settings. X-Vine also helps protect the privacy of users social network contacts and keeps their IP addresses hidden from those outside of their social circle, providing a basis for pseudonymous communication. We first evaluate our design with analysis and simulations, using several real world large-scale social networking topologies. We show that the constraints of X-Vine allow the insertion of only a logarithmic number of Sybil identities per attack edge; we show this mitigates the impact of malicious attacks while not affecting the performance of honest nodes. Moreover, our algorithms are efficient, maintain low stretch, and avoid hot spots in the network. We validate our design with a PlanetLab implementation and a Facebook plugin.

cs.CR↗