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…

The paper argues that Agentic AI fundamentally breaks the historical security tradeoff between deception fidelity and scale, necessitating a shift from authenticating actors to evaluating actions.

The paper proposes a system that operationalizes cybersecurity governance frameworks by integrating them with attack-path modeling and Deep Reinforcement Learning to generate practical, resource-const…

The paper argues that AI security research is imbalanced, focusing too much on demonstrating attacks and not enough on developing practical, usable defenses.

The paper develops a formal theory to analyze how throughput changes in AI-enhanced cybersecurity pipelines when stage capacities are perturbed by multipliers.

The paper proposes PRAETORIAN, a novel defense mechanism for Graph Neural Networks (GNNs) that targets the intrinsic structural requirements of backdoor attacks, significantly reducing the attack succ…

The paper systematically maps LLM agent vulnerabilities by testing 10,000 prompt variations, finding that 'goal reframing' language is the primary trigger for exploitation, rather than broad adversari…

The paper proposes a bilevel optimization framework to model the adversarial co-evolution between malware attackers and detection models, achieving near-total immunity against sophisticated evasion at…

The paper introduces CyBiasBench, a comprehensive benchmark that quantifies the inherent, agent-specific bias in LLM agents' attack selection patterns in cybersecurity scenarios.

The paper designs an optimal mechanism for soliciting expensive computational tasks in adversarial blockchain environments, showing that the loss of optimality scales logarithmically with the cost of…

The paper introduces C-MADF, a causally constrained multi-agent framework that significantly reduces false positives in autonomous cyber defense by restricting response actions to structurally consist…

The paper introduces a threat-oriented digital twinning methodology to enable reproducible and controllable cybersecurity evaluation of autonomous platforms, overcoming limitations in accessing real-w…

The paper empirically evaluates various agentic architectures for offensive security tasks, finding that while broader coordination improves coverage, the optimal architecture is non-monotonic and dep…

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…

This paper develops a formal economic framework to assess the security of VDF-based randomness beacons, demonstrating that many proposed delays are economically insecure due to rational, profit-motiva…

The paper introduces ARCANE, a Bayesian network framework for cross-campaign cyber attribution, finding that while aggregating telemetry improves identification, structural feature limitations prevent…

This paper systematically measures and explains how sequential model defenses can conflict, finding that 38.9% of ordered defense sequences cause measurable risk exacerbation due to anti-aligned param…

The paper models the trade-off between deploying increasingly capable AI systems and managing associated cyber risks, finding a 'deployment paradox' where high-loss environments with weak governance l…

CoopGuard is a novel stateful, multi-round defense framework using cooperative agents to significantly reduce the success rate of evolving adversarial attacks against Large Language Models.

The paper analyzes how AI-driven adaptive adversaries exploit implementation-level weaknesses in Public Key Cryptography, suggesting that current algorithm-centric security models are insufficient.