This paper evaluates a novel black-box adversarial attack to demonstrate the vulnerability of ML-based IoT Intrusion Detection Systems (IDS) and proposes a robust defense mechanism to mitigate these e…

The paper introduces Kumo, a novel security-focused simulator that enables controlled analysis of resource sharing and scheduling risks in serverless cloud environments, demonstrating that scheduler c…

The paper proposes a dynamic queueing framework that estimates an organization's cyber resources and attack surface dynamics by analyzing the timestamps of vulnerabilities and fixes, achieving high ac…

The paper introduces an open-source security framework that significantly improves cloud infrastructure security assessment by unifying identity and resource data, reducing false positives, and automa…

FlowGuard introduces an identity-independent defense using flow matching to detect data-free model stealing attacks by identifying synthetic queries as out-of-distribution based on their lower-dimensi…

This paper proposes an MLOps architecture using Kubeflow to automatically detect adversarial attacks on AI models deployed in Kubernetes and deploy robust defenses to maintain model accuracy.

The paper introduces Honeyval, a comprehensive evaluation framework, to rigorously test LLM-powered HTTP honeypots, demonstrating that these honeypots provide substantially longer and harder-to-detect…

The paper introduces Honeyval, a comprehensive evaluation framework, to rigorously test LLM-powered HTTP honeypots, demonstrating that these systems provide substantially longer and harder-to-detect i…

AEGIS introduces a novel physics-based system that analyzes encrypted network traffic flow dynamics, achieving state-of-the-art zero-day evasion detection with high accuracy and low latency.

The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

This paper analyzes darknet traffic to characterize advanced, AI-assisted bot reconnaissance, finding that modern evasion techniques allow most bot traffic to bypass standard IDS thresholds.

The paper introduces a queueing-theoretic framework to model dynamic cyber-attack surfaces, developing an adaptive reinforcement learning defense policy that significantly reduces active vulnerabiliti…

The paper introduces Landseer, a modular framework designed to systematically evaluate and compose multiple machine learning defenses to address complex, real-world security requirements.

The paper demonstrates that current defenses against malicious fine-tuning of foundation models are insufficient because they only address fixed attacks, and introduces a unified adaptive attack that…

The paper introduces a novel stateful online monitoring system that detects distributed multi-agent cyberattacks by aggregating weak suspiciousness signals across many user accounts, overcoming the bl…

The paper introduces a novel stateful online monitoring system that detects distributed multi-agent cyberattacks by aggregating weak suspiciousness signals across many user accounts, overcoming the bl…

The paper demonstrates that simpler, shallower Deep Neural Network architectures with reduced features and ReLU activations can inherently improve the robustness of ML-NIDS against gradient-based adve…

This paper systematically analyzes the threat posed by malicious third-party API routers in the LLM supply chain, finding that a significant number of routers actively perform payload injection, crede…

EnCAgg proposes a novel robust aggregation method for federated learning that uses reference clients and advanced clustering techniques to accurately filter dynamic model poisoning attacks while minim…

The paper evaluates AI's effectiveness in detecting network intrusions and cryptographic side-channel leakage, finding high accuracy in stable environments but performance degradation with novel traff…