Related papers: PSR2: A Phase-based Semantic Reasoning Framework f…
Large language models (LLMs) excel at mathematical reasoning and logical problem-solving. The current popular training paradigms primarily use supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance the models' reasoning…
Smart contract-based automation of financial derivatives offers substantial efficiency gains, but its real-world adoption is constrained by the complexity of translating financial specifications into gas-efficient executable code. In…
Logic provides a controlled testbed for evaluating LLM-based reasoners, yet standard SAT-style benchmarks often conflate surface difficulty (length, wording, clause order) with the structural phenomena that actually determine…
The advent of blockchain technology has facilitated the widespread adoption of smart contracts in the financial sector. However, current fraud detection methodologies exhibit limitations in capturing both global structural patterns within…
Even though much progress has been made in identifying and mitigating smart contract vulnerabilities, we often hear about coding or design issues leading to great financial losses. This paper presents our progress toward finding defects…
Fault diagnosis is critical for the safe operation of industrial systems. Conventional diagnosis models typically produce abstract outputs such as anomaly scores or fault categories, failing to answer critical operational questions like…
Referring Remote Sensing Image Segmentation (RRSIS) aims to segment target objects in remote sensing (RS) images based on textual descriptions. Although Segment Anything Model 2 (SAM2) has shown remarkable performance in various…
Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is…
This paper presents VulnSense framework, a comprehensive approach to efficiently detect vulnerabilities in Ethereum smart contracts using a multimodal learning approach on graph-based and natural language processing (NLP) models. Our…
Smart contract vulnerabilities have led to significant financial losses, with their increasing complexity rendering outright prevention of hacks increasingly challenging. This trend highlights the crucial need for advanced forensic analysis…
Background. Developers use Automated Static Analysis Tools (ASATs) to control for potential quality issues in source code, including defects and technical debt. Tool vendors have devised quite a number of tools, which makes it harder for…
Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables…
This paper introduces a new technique for dynamic verification of component-based real-time systems based on statistical inference. Verifying such systems requires checking two types of properties: functional and real-time. For functional…
This paper shows how knowledge representation and reasoning techniques can be used to support organizations in complying with the GDPR, that is, the new European data protection regulation. This work is carried out in a European H2020…
Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code…
Advanced Persistent Threats (APTs) are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit…
Designing robotic systems to act autonomously in unforeseen environments is a challenging task. This work presents a novel approach to use formal verification, specifically Statistical Model Checking (SMC), to verify system properties of…
Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem. In this paper, we study the faithfulness of existing systems from a new perspective of…
Automating the detection of EU General Data Protection Regulation (GDPR) violations in source code is a critical but underexplored challenge. We introduce \textbf{GDPR-Bench-Android}, the first comprehensive benchmark for evaluating diverse…
Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…