The paper proves that the reversible elementary second order cellular automaton rule 115 is periodic when started on finite initial configurations.

The paper introduces Acceptance Cards, a rigorous four-diagnostic standard, to provide a comprehensive and reliable evaluation protocol for claims of safe fine-tuning defenses.

The paper introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.

The paper introduces Fine-Tuning Integrity (FTI), a security goal that uses Succinct Model Difference Proofs (SMDPs) to cryptographically prove that a fine-tuned model update adheres to specific struc…

The paper evaluates an automated legal triage system (FETCH) that uses follow-up questions, demonstrating that while low-cost LLMs are effective for classification, generating high-quality questions r…

The paper argues that post-hoc mitigation techniques like machine unlearning are insufficient to cure legal liability arising from the unlawful acquisition and training on copyrighted data, advocating…

This paper demonstrates that YARA rules, even when stripped of metadata, contain enough stylistic information to accurately infer the original source repository, author, and even the malware family.

This paper provides the first longitudinal analysis of log-based detection rule evolution in public repositories, finding that rule changes reflect ongoing operational trade-offs rather than steady co…

RuleForge is an automated system that generates and validates detection rules for web vulnerabilities from structured CVE templates, significantly improving detection accuracy and reducing false posit…

The paper proposes and tests a novel, non-security 'Recuse Signal'—an in-band signal—to allow operators to tell autonomous LLM agents to voluntarily withdraw access, demonstrating that compliant agent…

The paper introduces a deterministic method to automatically synthesize initial SIEM detection rules (Sigma rules) from attack simulation findings, ensuring full traceability back to the specific orig…

The paper introduces WIRE, a pipeline for diagnosing live intra-policy rule conflicts in LLM agents by identifying and testing specific rule pairs within a single prompt policy that can co-govern a re…

PIIGuard introduces a novel webpage-level defense mechanism using optimized hidden HTML fragments to prevent LLM assistants from scraping contact-style PII, achieving high defense success rates while…

The authors created ImmigrationQA, a large source-grounded QA dataset for U.S. immigration law, and fine-tuned a small language model (Llama 3.2 3B) on it, achieving a significant performance boost ov…

The paper introduces Security Level 5 (SL5), a new, highly stringent security standard for AI systems designed to withstand attacks from state-level, top-tier cyber adversaries.

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

The paper proposes Proof-Carrying Agent Actions (PCAA), a runtime-neutral governance model that uses action certificates to consistently track and authorize high-risk actions across diverse and hetero…

The paper investigates predictive multiplicity and arbitrariness in recidivism risk assessment, finding that similarly accurate models often exhibit high predictive agreement, and proposes a simple po…

The paper investigates generalized Wall-Sun-Sun primes, $WSS(d)$, and uses them to study the weight distributions of specific cyclic codes defined over $ ext{F}_p$ and $ ext{Z}_{p^2}$.

The paper introduces DrugClaw, a multi-agent system, and DrugAudit, a new benchmark, demonstrating that DrugClaw excels at answering drug-related questions by grounding answers in primary regulatory s…