This paper presents a novel approach for constructing information flow paths from RTL trace data for automated property generation and validation in hardware design.

The paper proposes a secure conformance checking method that allows a party to verify an event log against a process model while protecting the sensitive data within the log using homomorphic encrypti…

The paper introduces NeuroTaint, a novel taint tracking framework that adapts information flow analysis for LLM agents by modeling taint propagation as semantic transformation and causal influence, si…

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

The paper introduces OpenClawBench, a large-scale dataset and framework for measuring process-side anomalies in real-world agent execution trajectories, demonstrating that task success does not guaran…

The paper proposes a novel method to automatically enforce differential privacy in stream-based runtime monitoring specifications by analyzing temporal dependencies and injecting calibrated noise.

The paper introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…

The paper proposes a secure, privacy-preserving method for conformance checking using homomorphic encryption and string processing algorithms, allowing the check to be performed without exposing the p…

The paper proposes a structural method using decision tree rulesets and multiple complementary metrics to detect concept drift in evolving malware families, finding that fixed-interval windowing with…

This comprehensive systematic review synthesizes decades of research on web tracker detection, proposing a new taxonomy and identifying key open research gaps to guide future work.

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 MemTrace, a framework that treats LLM memory pipelines as traceable graphs to systematically diagnose and automatically correct memory-related errors, boosting performance by up t…

This paper empirically evaluates the use of Retrieval-Augmented Generation (RAG) for malware explanation and finds that RAG frequently degrades explanation quality by adding noise when structured secu…

MalwarePT introduces a novel binary-level foundation model, pretrained on Windows PE code-section bytes using a ModernBERT-style encoder, demonstrating superior transfer learning capabilities across v…

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…

The paper proposes a novel framework, Speculative Non-Interference (SNI), and a tool, Spectector, to formally detect and verify security vulnerabilities arising from complex interactions of multiple s…

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…

This paper analyzes large-scale reasoning traces from LLM-based binary vulnerability analysis, identifying four structured, token-level implicit patterns that govern how LLMs explore code paths.

Agentproof is a system that provides static, pre-deployment verification of safety properties in agent workflow graphs by automatically extracting a unified graph model and applying structural and tem…