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…

This study empirically measures the consistency and success rate of autonomous LLM penetration testing across multiple services, finding statistically significant differences in exploitation capabilit…

This study empirically measures the consistency and effectiveness of autonomous LLM penetration testing across multiple services, finding statistically significant differences in exploitation rates am…

The paper introduces CyberCertBench, a new benchmark suite for evaluating LLMs against industry cybersecurity certifications, finding that while frontier models perform well on general knowledge, thei…

LLM-FACETS introduces an open-source, privacy-preserving framework designed to enable non-technical domain experts and compliance officers to audit and evaluate the transparency and accountability of…

The paper evaluates graph-context LLM defenders against multi-round, adaptive fraud attacks, finding that while graph context improves early safety, it significantly increases benign over-refusal due…

This paper provides the first comprehensive Systematization of Knowledge (SoK) on the security aspects of LLM-as-a-Judge (LaaJ) systems, identifying key vulnerabilities and proposing a taxonomy for fu…

The paper introduces ML-Bench, a policy-grounded multilingual safety benchmark, and ML-Guard, a superior guardrail model that enables culturally and legally aligned safety assessment for LLMs across 1…

The paper evaluates frontier LLMs on cybersecurity tasks using dual-mode benchmarks and concludes that general-purpose models are insufficient, advocating for specialized, vertical foundation models.

The paper measures the specific defensive contribution of various LLM security controls, demonstrating that while defenses like refusal filters and budget controls are effective, they are susceptible…

The paper introduces SecLens-R, a multi-stakeholder evaluation framework, demonstrating that LLM performance for vulnerability detection varies significantly depending on the specific priorities (e.g.…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper proposes a trust-boundary architecture using Lean 4 to verify the deterministic structured computations surrounding LLM pipelines, providing verifiable certificates for high-stakes deploymen…

The paper proposes an attestation-aware promotion gate to mitigate supply-chain risks in LLM pipelines by cryptographically verifying and enforcing claims about training and release artifacts before d…

The paper introduces FinVerBench, a comprehensive benchmark for financial statement verification, concluding that successful verification requires calibrated judgment under realistic observational con…

This paper benchmarks LLMs for smart contract security analysis, concluding that while LLMs show potential, their reliability is limited by lexical bias and requires integration with traditional stati…

The paper introduces SIGIL, a novel framework that cryptographically seals the entire lifecycle of LLM skills, ensuring verifiable integrity from publication through runtime execution to prevent suppl…

The paper proposes FinSec, a novel four-tier security detection framework, to robustly identify complex financial risks and suspicious dialogue patterns in LLM-powered financial agents, achieving stat…

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 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.