PISmith

PISmith: 基于强化学习的红队攻击以防御提示注入（COLM 2026） 这是 PISmith: 基于强化学习的红队攻击以防御提示注入 的官方实现。 环境设置 PISmith 已在 Python 3.10 和 CUDA 版本 12.9 下测试通过。 1. 创建 Python 3.10 conda 环境 root@kitploit: conda create -n PISmith python=3.10 -y conda activate PISmith 2. 安装依赖 root@kitploit: pip install -r requirements.txt 3...

GuardReasoner-VL

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Yue Liu, Shengfang Zhai, Mingzhe Du Yulin Chen, Tri Cao, Hongcheng Gao, Cheng Wang Xinfeng Li, Kun Wang, Junfeng Fang, Jiaheng Zhang, Bryan Hooi 1National University of Singapore, 2Nanyang Technological University To enhance the safety ...

StealthRL

StealthRL: 複数のAIテキスト検出器を回避する強化学習パラフレーズ攻撃 論文（arXiv） デモ モデル（Hugging Face） ベンチマークデータセット（Hugging Face 要約...

CyberBattleSim

CyberBattleSim 2021年4月8日: Microsoft Security Blogのアナウンスをご覧ください。 CyberBattleSimは、シミュレートされた抽象的なエンタープライズネットワーク環境で動作する自動化エージェントの相互作用を調査するための実験研究プラットフォームです。このシミュレーションは、コンピュータネットワークとサイバーセキュリティの概念を高レベルで抽象化しています。PythonベースのOpen AI Gymインターフェースにより、強化学習アルゴリズムを使用した自動化エージェントのトレーニングが可能です。...

hontel

HonTel HonTel is a Honeypot for Telnet service. Basically, it is a Python v2.x application emulating the service inside the chroot environment. Originally it has been designed to be run inside the Ubuntu/Debian environment, though it could be easily adapted to run inside any Linux environment...

AutoPentest-DRL

AutoPentest-DRL: 深層強化学習を用いた自動侵入テスト...

Pesidious

深層強化学習とGANを用いたマルウェア変異 このツールの目的は、人工知能を使ってマルウェア（PE32のみ）サンプルを変異させ、AIを搭載した分類器を回避しつつ、その機能を維持することです。過去には、研究者が強化学習または敵対的生成ネットワーク（GAN）を武器に選び、マルウェア実行ファイルの状態を変更してアンチウイルスエージェントを欺くという注目すべき研究が行われてきました。私たちのソリューションは、深層強化学習とGANを組み合わせて、以下に示すようにこれらのアプローチを単独で使用した場合の限界の一部を克服しています。 .png ツールの完全なドキュメントはこちらにあります。 インストール...

OpenAI Pauses Frontier RL Training as It Tightens Defenses Against Unsafe AI Behavior

OpenAI on Tuesday revealed that it paused reinforcement learning RL training for its latest artificial intelligence AI models for two weeks while it shored up additional defenses and increased the scope of its monitoring to avert another Hugging Face-like incident. "As models become more capable,...

CVE-2026-63232

A SQL injection and unsafe deserialisation vulnerability in Koollab LMS allowed an authenticated attacker to inject through the assessment reinforcement endpoint, control data passed to unserialize, write a webshell to a publicly accessible location, and execute arbitrary code on the server...

EUVD-2026-50127

A SQL injection and unsafe deserialisation vulnerability in Koollab LMS allowed an authenticated attacker to inject through the assessment reinforcement endpoint, control data passed to unserialize, write a webshell to a publicly accessible location, and execute arbitrary code on the server...

PT-2026-65703

A SQL injection and unsafe deserialisation vulnerability in Koollab LMS allowed an authenticated attacker to inject through the assessment reinforcement endpoint, control data passed to unserialize, write a webshell to a publicly accessible location, and execute arbitrary code on the server...

ARTA: Adaptive Reinforcement-Learning-Based Throttling Agent for RowHammer Vulnerabilities

RowHammer vulnerability continues to intensify with DRAM scaling, reducing the activation threshold needed to induce bitflips and rendering existing defenses such as TRR, ECC, and refresh-based mechanisms vulnerable to sophisticated multi-bank hammering patterns. This work presents ARTA, a...

A Red Teaming Framework for Evaluating Robustness of AI-Enabled Security Orchestration, Automation, and Response Systems

AI-enabled Security Orchestration, Automation, and Response SOAR systems increasingly employ autonomous agents for cyber defense, yet their resilience to adaptive adversaries is underexplored. We introduce an autonomous red teaming framework that integrates large language models LLMs with...

Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning

We address a fundamental challenge in cybersecurity operations of translating governance frameworks into actionable mitigation decisions under realistic resource constraints. Frameworks such as the NIST Cybersecurity Framework CSF provide widely adopted measures of organizational maturity, but do...

STARE: Step-Wise Temporal Alignment and Red-Teaming Engine for Multi-Modal Toxicity Attack

Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, returning only terminal toxicity scores and leaving open the question of when and how toxic semanti...

XekRung Technical Report

We present XekRung, a frontier large language model for cybersecurity, designed to provide comprehensive security capabilities. To achieve this, we develop diverse data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable construction of high-quality training data and...

Risk Models As Mediating Artifacts: A Postphenomenological Analysis of the CIIM Framework in Cybersecurity Practice

This article applies postphenomenological theory to the field of cybersecurity risk management, arguing that formal risk models function as mediating artifacts that shape how security practitioners or analysts perceive, interpret, and act on threats. Based on Don Ihde's taxonomy on human-technolo...

VeRL 权限许可和访问控制问题漏洞

VeRL is an open-source reinforcement learning framework developed by ByteDance, aimed at optimizing large model training and inference processes. Versions of VeRL prior to 0.7.0 contained vulnerabilities related to permission licensing and access control. These vulnerabilities stemmed from a...

Adaptive Instruction Composition for Automated LLM Red-Teaming

Many approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target. Several of them task the attacker with identifying effective strategies through trial and error, resulting in a semantically limited range of successes. Another approach discovers diverse attacks ...

TL-RL-FusionNet: An Adaptive and Efficient Reinforcement Learning-Driven Transfer Learning Framework for Detecting Evolving Ransomware Threats

Modern ransomware exhibits polymorphic and evasive behaviors by frequently modifying execution patterns to evade detection. This dynamic nature disrupts feature spaces and limits the effectiveness of static or predefined models. To address this challenge, we propose TL-RL-FusionNet, a reinforceme...