The paper introduces Dummy-Aware Weighted Attack (DAWA), a novel evaluation method that significantly reduces the reported robustness of Dummy Classes-based defenses by simultaneously targeting both t…

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

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…

The paper introduces STRIKE, a multi-dimensional structured taxonomy designed to provide a comprehensive and unified framework for classifying the rapidly evolving complexity of modern cybercrimes.

The paper systematically evaluates various defense mechanisms against persistent memory attacks on LLM agents, finding that only tool-gating at the memory layer (Memory Sandbox) effectively mitigates…

Defense training for LLM agents, intended to improve safety, systematically degrades their core competence, leading to unreliability in multi-step tasks.

This paper reviews advanced AI-based solutions, specifically combining LLMs and RL, to create dynamic and cost-effective network and device-level cyber deception strategies for contested environments.

This paper evaluates the assumption that decoy placement is possible for all MITRE ATT&CK v18.1 techniques and introduces a rubric for infrastructure deception.

This paper proposes using a zero-determinant (ZD) strategy to construct an effective Moving Target Defense (MTD) that maintains performance comparable to the optimal Stackelberg equilibrium while dras…

This paper systematically analyzes 123 publications on anti-forensics to quantify techniques and attack vectors, identify research patterns, and propose directions for a more coherent and ethical unde…

The paper introduces a challenging benchmark for LLM agents to perform unsupervised threat hunting on raw Windows event logs, finding that current frontier models perform poorly and are not ready for…

The paper identifies a critical vulnerability, the Camouflage Detection Gap (CDG), where standard LLM injection detectors fail dramatically when malicious payloads mimic the target domain's language a…

This paper uses Colonel Blotto game models, grounded in Routine Activity Theory, to determine the optimal allocation of defensive resources against social engineering attacks, providing data-driven de…

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 reveals a denial-of-service vulnerability in LLM-based guardrails for autonomous agents and proposes two attack frameworks.

This paper provides a systematic, layered review of security risks and defense strategies for autonomous agent frameworks, using OpenClaw as a case study to address the current lack of integrated rese…

The paper introduces a defense-placement taxonomy for the Model Context Protocol (MCP) to systematically analyze security gaps, revealing that many vulnerabilities stem from architectural misalignment…

The paper introduces Indirect Harm Optimization (IHO), a novel black-box, adaptive, and efficient attack method that significantly improves jailbreak success rates against LLMs, aiming to provide a st…

The paper introduces Poison-with-Style (PwS), a stealthy model poisoning attack that exploits developers' inherent code styles as covert triggers to make Code LLMs generate vulnerable code without exp…