kong

Kong: 自主逆向工程师 用于逆向工程二进制文件的LLM编排 Kong是什么？ 大多数任务遵循线性关系：任务越难，通常耗时越长。逆向工程（及二进制分析）是一种任务，其实际难度其实并不高，但执行时间却可能长达数小时甚至数天，即使是只有几百个函数的二进制文件也是如此。 Kong 使用NSA级别的逆向工程框架，将机械层自动化。Kong 可以接收一个完全混淆且剥离了符号的二进制文件，运行完整的分析管线：对函数进行分类、构建调用图上下文、通过LLM引导的反编译恢复类型和符号，并将结果写回 Ghidra 的程序数据库。输出的二进制文件中，某个 FUN00401a30 变成了...

inspect_petri

Inspect Petri 欢迎使用 Inspect Petri，一个审计代理，能够实现语言模型的自动监控与交互，以检测潜在的对齐问题、奖励破解及其他令人担忧的行为。 Petri 帮助你快速端到端地测试具体的对齐假设。它能够： 生成逼真的审计场景（通过你的种子指令） 使用审计模型和目标模型编排多轮审计 模拟工具和回滚以测试行为 使用一致评分标准的评判模型对对话记录进行打分 了解更多关于 Petri 的使用方法，请访问 https://meridianlabs-ai.github.io/inspectpetri。 !NOTE 这是 Petri 3.0 版本。虽然大多数 CLI 命令与...

oss-fuzz-gen

Un framework para la generación y evaluación de fuzz targets Este framework genera fuzz targets para proyectos reales de C/C++/Java/Python con varios modelos de lenguaje de gran tamaño LLM y los evalúa mediante la plataforma OSS-Fuzz. Más detalles disponibles en Fuzzing impulsado por IA: rompiend...

www-project-top-10-for-large-language-model-applications

www-project-top-10-for-large-language-model-applications Repositorio Web de la Fundación OWASP OWASP Top 10 para Aplicaciones de Grandes Modelos de Lenguaje ¡Bienvenido al repositorio oficial del OWASP Top 10 para Aplicaciones de Grandes Modelos de Lenguaje! Acerca de Este Repositorio Este...

aegis-audio-defense

AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks Submitted to ICASSP 2027. AEGIS keeps the target audio-language model frozen and adds a mid-layer risk gate that conditionally drives late-layer safety adapters, with closed-loop scaling at...

markdown-exfil-tester

valtik-markdown-exfil-tester Probador de caja negra para inyección indirecta de instrucciones que conduce a la exfiltración de markdown / HTML en chatbots basados en LLM. Esta es la clase de vulnerabilidad que afectó a Microsoft 365 Copilot CVE-2025-32711, también conocido como EchoLeak, ChatGPT...

deleting-the-trace

Ataques de inyección de tokens de control contra agentes que utilizan herramientas Código y mediciones registradas para un estudio de dos ataques a nivel de entrada contra agentes de modelos de lenguaje que utilizan herramientas. El primer ataque añade una cadena corta de los propios tokens de...

EntropicaPublic

Actualizaciones de marzo Necesito trasladar algo de trabajo desde los repositorios privados. Continúa la exploración del uso de modelos masivamente multicabezales con funciones de mezcla y lectura separadas. Actualmente estoy entrenando un Chinese TinyStories en un modelo equivalente a 3B que se...

batch_jailbreak

Repositorio oficial de Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting Kihyun Kim, Hee-Seon Kim, Wonjun Lee, Changick Kim Korea Advanced Institute of Science and Technology KAIST Noticias 2026.09 ¡Nuestro artículo ha sido aceptado en AACL-IJCNLP 2026 Main! 🎉...

birdy-edwards

BIRDY-EDWARDS 2.0 Infiltrar y Exponer Herramienta automatizada de inteligencia de Facebook impulsada por IA para perfilado de objetivos, análisis de redes y reporte de amenazas. Se ejecuta completamente en el dispositivo mediante Ollama. Plataforma SOCMINT de Facebook impulsada por IA — 100% loca...

CVE-2026-54559

PocketSphinx is a small speech recognizer. Prior to 5.1.1, the trie language-model loaders in src/lm/ngrammodeltrie.c do not adequately validate boundary conditions in ARPA, DMP, and binary format headers, and the acoustic-model loaders in src/mdef.c and src/util/bio.c use sscanf with unbounded...

CVE-2026-54559 PocketSphinx: Buffer overflows in language and acoustic model loading code

PocketSphinx is a small speech recognizer. Prior to 5.1.1, the trie language-model loaders in src/lm/ngrammodeltrie.c do not adequately validate boundary conditions in ARPA, DMP, and binary format headers, and the acoustic-model loaders in src/mdef.c and src/util/bio.c use sscanf with unbounded...

CVE-2026-54559 PocketSphinx: Buffer overflows in language and acoustic model loading code

PocketSphinx is a small speech recognizer. Prior to 5.1.1, the trie language-model loaders in src/lm/ngrammodeltrie.c do not adequately validate boundary conditions in ARPA, DMP, and binary format headers, and the acoustic-model loaders in src/mdef.c and src/util/bio.c use sscanf with unbounded...

CVE-2026-54559

PocketSphinx (a lightweight speech recognizer, including its Python bindings) versions 5prealpha through 5.1.0 are affected by buffer overflow vulnerabilities in its model-loading code. The trie language-model loaders in src/lm/ngram_model_trie.c fail to validate boundary conditions in ARPA, DMP,...

EEF-CVE-2026-78230 AshAi aggregate tool can read field-policy-protected fields

Summary AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type min, max, sum, avg that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value. Ash field policies redact forbidden fields on returned records replacing...

EUVD-2026-72924

AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type min, max, sum, avg that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value. Ash field policies redact forbidden fields on returned records replacing them with...

Using LLMs to Elicit Security Requirements for Service-Oriented Cyber Ranges

Cyber ranges are complex environments comprising many interacting components and stakeholders with different security concerns. The Service-Oriented Cyber Range SOR is no exception, particularly when it comes to training scenarios targeting critical infrastructure. Security concerns are translate...

PT-2026-81211

U-Boot before 2026.10-rc5 contains a use-after-free vulnerability in the httpc recv cb function within the lwIP wget implementation. When HTTP data storage fails, the callback frees the connection PCB but returns ERR BUF instead of ERR ABRT, causing the TCP input path to access released memory an...

CVE-2026-72742

DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The...

EUVD-2026-56886

DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The...