Related papers: Microarchitectural Security of AWS Firecracker VMM…
Trigger-Action platforms are an emerging class of web-based systems that enable users to create automation rules (or recipes) of the form, "If there is a smoke alarm, then turn off my oven." These platforms stitch together various online…
Constructing stealthy malware has gained increasing popularity among cyber attackers to conceal their malicious intent. Nevertheless, the constructed stealthy malware still fails to survive the reverse engineering by security experts.…
The asset trading volume on blockchain-based exchanges (DEX) increased substantially since the advent of Automated Market Makers (AMM). Yet, AMMs and their forks compete on the same blockchain, incurring unnecessary network and block-space…
The distributed data storage systems are constructed by large number of nodes which are interconnected over a network. Each node in such peer-to-peer network is vulnerable and at a potential risk for attack. The attackers can eavesdrop the…
Model hijacking can cause significant accountability and security risks since the owner of a hijacked model can be framed for having their model offer illegal or unethical services. Prior works consider model hijacking as a training time…
We present a new and practical framework for security verification of secure architectures. Specifically, we break the verification task into external verification and internal verification. External verification considers the external…
First, this case study explores an Intrusion Detection System package called Snort (provided by Cisco Systems) in a cloud environment. Snort is an open source and highly scalable signature-based intrusion detection system. Here, Snort is…
In cloud computing environments with many virtual machines, containers, and other systems, an epidemic of malware can be highly threatening to business processes. In this vision paper, we introduce a hierarchical approach to performing…
Despite existing work in machine learning inference serving, ease-of-use and cost efficiency remain challenges at large scales. Developers must manually search through thousands of model-variants -- versions of already-trained models that…
Recent research shows that colluded malware in different VMs sharing a single physical host may use a resource as a channel to leak critical information. Covert channels employ time or storage characteristics to transmit confidential…
Existing evaluations of AI misuse safeguards provide a patchwork of evidence that is often difficult to connect to real-world decisions. To bridge this gap, we describe an end-to-end argument (a "safety case") that misuse safeguards reduce…
The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…
In their continuous growth and penetration into new markets, Field Programmable Gate Arrays (FPGAs) have recently made their way into hardware acceleration of machine learning among other specialized compute-intensive services in cloud data…
Blockchains are distributed secure ledgers to which transactions are issued continuously and each block of transactions is tightly coupled to its predecessors. Permissioned blockchains place special emphasis on transactions throughput. In…
Website Fingerprinting (WF) attacks raise major concerns about users' privacy. They employ Machine Learning (ML) to allow a local passive adversary to uncover the Web browsing behavior of a user, even if she browses through an encrypted…
Side channel attacks are a major class of attacks to crypto-systems. Attackers collect and analyze timing behavior, I/O data, or power consumption in these systems to undermine their effectiveness in protecting sensitive information. In…
Existing serverless workflow orchestration systems are predominantly designed for a single-cloud FaaS system, leading to vendor lock-in. This restricts performance optimization, cost reduction, and availability of applications. However,…
Microarchitectural security verification of software has seen the emergence of two broad classes of approaches. The first is based on semantic security properties (e.g., non-interference) which are verified for a given program and a…
Trusted Execution Environments (TEEs) on low-power microcontrollers (e.g., ARM TrustZone-M) enable isolation of Secure and Non-Secure software but still require both worlds to share resources, including interrupt controllers. In this model,…
Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…