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 models the cybersecurity arms race using a contest-theoretic framework, showing that full cross-correlation of threat intelligence can neutralize the attacker's structural advantage from inc…

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 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…

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 argues that much of the existing research on Federated Learning (FL) security is based on idealized assumptions, and provides a practical evaluation framework showing that real-world attack…

The paper establishes a standardized security assessment framework and develops a multi-layered defensive system, demonstrating that systematic testing and external defenses are crucial for safe LLM d…

The paper demonstrates that linking team bonus points to measurable security improvements significantly reduces code security issues in a controlled educational experiment.

The paper argues that LLM agent security is fundamentally an agent-human interaction (AHI) problem, demonstrating that industry practices rely on human-centric mechanisms while academic research focus…

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

The paper proposes IntraGuard, a black-box, venue-agnostic defense framework that embeds hidden instructions into manuscripts via PDF structure to disrupt AI-generated peer reviews, achieving up to 84…

This paper empirically demonstrates that the architectural design of multi-agent systems significantly impacts their security, finding that coordination mechanisms can introduce vulnerabilities greate…

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…

This paper proposes a gap-prioritization framework to bridge the gap between theoretical cyber attack prediction research and practical operational deployment by identifying critical implementation hu…

The paper demonstrates that confronting Large Reasoning Models (LRMs) with conflicting objectives, such as contradictory choices or conflicting alignment values, significantly increases their vulnerab…

This paper provides the first comprehensive, end-to-end survey dedicated to the security of Retrieval-Augmented Generation (RAG) systems, systematically mapping threats, defenses, and benchmarks acros…

The paper proposes SafeReview, a co-evolutionary adversarial training framework that significantly improves the robustness of LLM-based peer review systems against sophisticated adversarial hidden pro…

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are…

The paper benchmarks current frontier computer-using agents against hand-crafted attacks, finding that while they are highly safe in browser tasks, this safety does not generalize to other domains lik…

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…