SAFE

SAFE SAFE 对研究工件中的 Semgrep 和 Trivy 发现执行受控的、仓库感知的安全评估。 它支持两个独立的分类任务：直接的 binary 预测（SECURITYRELEVANT 或 NONSECURITY）以及详细的 multiclass 上下文分类法（三个标签 — 参见 三个标签）。每个任务都可以在零样本或代理模式下运行。 它仅需要： 1. 一个以分号分隔的发现 CSV 文件。 2. 一个目录，其中每个 artifactid 对应一个研究工件文件夹。 3. 可选地，一个按 artifactid 键控的论文 PDF/文本集合。 4. 一个 OpenAI API 密钥或对组...

Agentic-CLIP-Benchmark

Agentic-CLIP-Benchmark: Zero-Shot Evaluation on CIFAR-10 -green.svg This project implements a robust, automated pipeline for evaluating OpenAI's CLIP ViT-B/32 model on the full CIFAR-10 test set 10,000 images. Developed using an AI Native workflow Trae IDE , it achieves a high-precision zero-shot...

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts

The deployment of large language models LLMs in Swiss financial and regulatory contexts demands empirical evidence of both production reliability and adversarial security, dimensions not jointly operationalized in existing Swiss-focused evaluation frameworks. This paper introduces Swiss-Bench 003...

CVE-2026-23654

Dependency on vulnerable third-party component in GitHub Repo: zero-shot-scfoundation allows an unauthorized attacker to execute code over a network...

NASimJax: GPU-Accelerated Policy Learning Framework for Penetration Testing

Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a complex sequential decision-making task that is inherently partially observable and features large action spaces. Training reinforcement learning RL policies for this domain faces a fundamental...

EUVD-2026-10577

Dependency on vulnerable third-party component in GitHub Repo: zero-shot-scfoundation allows an unauthorized attacker to execute code over a network...

EUVD-2026-10578

Dependency on vulnerable third-party component in GitHub Repo: zero-shot-scfoundation allows an unauthorized attacker to execute code over a network...

CVE-2026-23654

Dependency on vulnerable third-party component in GitHub Repo: zero-shot-scfoundation allows an unauthorized attacker to execute code over a network...

CVE-2026-23654

Dependency on vulnerable third-party component in GitHub Repo: zero-shot-scfoundation allows an unauthorized attacker to execute code over a network...

CVE-2026-23654 GitHub: Zero Shot SCFoundation Remote Code Execution Vulnerability

...

CVE-2026-23654 GitHub: Zero Shot SCFoundation Remote Code Execution Vulnerability

...

Microsoft GitHub Repo: Zero Shot scFoundation 安全漏洞

Microsoft GitHub Repo: Zero Shot scFoundation is a biological information research code base owned by Microsoft Corporation. There are security vulnerabilities present in Microsoft GitHub Repo: Zero Shot scFoundation. Attackers can exploit these vulnerabilities to execute code remotely...

SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection

Large language models LLMs have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description language HDL datasets. This knowledge gap constrains LLM performan...

MultiVer: Zero-Shot Multi-Agent Vulnerability Detection

We present MultiVer, a zero-shot multi-agent system for vulnerability detection that achieves state-of-the-art recall without fine-tuning. A four-agent ensemble security, correctness, performance, style with union voting achieves 82.7% recall on PyVul, exceeding fine-tuned GPT-3.5 81.3% by 1.4...

LLM-FS: Zero-Shot Feature Selection for Effective and Interpretable Malware Detection

Feature selection FS remains essential for building accurate and interpretable detection models, particularly in high-dimensional malware datasets. Conventional FS methods such as Extra Trees, Variance Threshold, Tree-based models, Chi-Squared tests, ANOVA, Random Selection, and Sequential...

Benchmarking Large Language Models for Zero-Shot and Few-Shot Phishing URL Detection

The Uniform Resource Locator URL, introduced in a connectivity-first era to define access and locate resources, remains historically limited, lacking future-proof mechanisms for security, trust, or resilience against fraud and abuse, despite the introduction of reactive protections like HTTPS...

Lightweight LLMs for Network Attack Detection in IoT Networks

The rapid growth of Internet of Things IoT devices has increased the scale and diversity of cyberattacks, exposing limitations in traditional intrusion detection systems. Classical machine learning ML models such as Random Forest and Support Vector Machine perform well on known attacks but requir...

Evaluation of Vision-LLMs in Surveillance Video

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of anomalous or criminal events is crucial for effective...

Automated Cyber Defense with Generalizable Graph-Based Reinforcement Learning Agents

Deep reinforcement learning RL is emerging as a viable strategy for automated cyber defense ACD. The traditional RL approach represents networks as a list of computers in various states of safety or threat. Unfortunately, these models are forced to overfit to specific network topologies, renderin...

Can Multi-Modal (Reasoning) LLMs Detect Document Manipulation?

Document fraud poses a significant threat to industries reliant on secure and verifiable documentation, necessitating robust detection mechanisms. This study investigates the efficacy of state-of-the-art multi-modal large language models LLMs-including OpenAI O1, OpenAI 4o, Gemini Flash thinking,...