INTACT
siyuanli00/intactResearch code reproducing multi-turn LLM jailbreak experiments (FITD, MRCJ, ActorAttack, X-Teaming) from the SoK intent-oriented systematization…
adversarial-attackai-securityeducation+2
5
siyuanli00/intactResearch code reproducing multi-turn LLM jailbreak experiments (FITD, MRCJ, ActorAttack, X-Teaming) from the SoK intent-oriented systematization…
owasp/trisuella-aidlca-frameworkPolicy-governed LLMSecOps framework providing AST-based SAST, secret scanning, supply-chain and multi-cloud CSPM checks, AI-BoM generation, and CI/CD…
qkrrkd90-source/weavemarkReference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…
george0papasotiriou/llm-jailbreak-via-chain-of-logic-injection-cve-2026-3098Multi-stage prompt injection technique that bypasses LLM safety alignment via identity reassignment, refusal suppression, and output coercion,…
giskard-ai/giskard-oss🐢 Open-Source Evaluation & Testing library for LLM Agents
s0ld13rr/pentestcodeAutonomous AI penetration testing agent that orchestrates multi-agent recon, exploitation, post-exploitation, and reporting with persistent…
ryehr/hitms_steganographyEmbed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…
cognitive-functors/c4-meta-systemProduction AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…
ragib-amin-nihal/pe-coaCode Implementation of "Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models"
unknownhl/deepguardCode for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"
vinsontang1/vultriageThe code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection
owasp/securemlSecureML - Securing and Watermarking AL models
owasp/sbom-vex-taint-analysisAutomated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX…
lightless-labs/third-thoughtsResearch toolkit for analyzing AI agent behavioral patterns through multi-disciplinary corpus analysis. Parses session logs, runs 23 analytical…
safelineman/agentic-soc-simulationAI 驱动的 SOC 仿真平台
lintsinghua/deepauditDeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。让安全不再昂贵，让审计不再复杂。
runanywhereai/on-device-browser-agentOn-device AI browser automation using WebLLM. No cloud, no API keys, fully private.
trailofbits/anamorpherimage scaling attacks for multi-modal prompt injection