This paper shows that for every fixed length t, cycles Ct and thetas Θt have the induced Erdős--Pósa property with respect to the induced minor relation in graphs.

The paper shows that an oddomorphism between graphs does not imply graph minor containment and introduces a new structural relation called split-off minor.

This paper introduces Stemma, a black-box LLM fingerprinting method that abstracts away surface-form variation and measures the inheritance of decision regions for reliable provenance testing.

The study evaluates how safety alignment affects autonomous security agents using a comprehensive trace-based benchmark, finding that while less-restricted models show gains, these effects are not uni…

This paper investigates the complexity of recognizing domatically critical graphs, which are graphs with maximum dominating sets that cannot be increased by deleting any edge.

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

Agent-Sentry is a runtime defense system that bounds the execution of LLM agents by learning a profile of benign behavior, effectively blocking malicious injections while maintaining high compatibilit…

The paper formalizes the concept of a causal pathway for rare events, showing that testable implications can be derived solely from this pathway abstraction, simplifying complex causal modeling.

This paper introduces the because-calculus, a calculus that structurally separates registration and attestation using dual effect rows and level-indexed typing, and proves the Conflation Theorem.

The paper introduces a truly benign Direct Preference Optimization (DPO) attack that can jailbreak large language models (LLMs) by fine-tuning them with minimal, harmless preference data, thereby supp…

The paper introduces PHTV-Scout, a novel framework that analyzes Douyin and Kwai data, revealing a high prevalence of potentially harmful teen videos, particularly CSE imagery, and demonstrating that…

The paper introduces 'abliteration,' a weight editing technique that successfully bypasses the refusal mechanism of safety-aligned Code LLMs, enabling scalable synthesis of vulnerable code from safe i…

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