LLM Adversarial Security Arena — Jailbreak → Detect → Defend → Verify

Elenchus MCP Server - Adversarial verification system for code review

AI safety evaluation framework testing LLM epistemic robustness under adversarial self-history manipulation

A marketplace of Claude Code plugins for adversarial security and architectural code review.

Systematic LLM jailbreak taxonomy — 40 attack patterns, 10 categories, empirical evaluation across 4 frontier models. AI safety research with responsible disclosure.

Benchmark LLM jailbreak resilience across providers with standardized tests, adversarial mode, rich analytics, and a clean Web UI.

Agent-driven adversarial paper audit framework

Adversarial MCP server benchmark suite for testing tool-calling security, drift detection, and proxy defenses

Systematic exploration of LLM alignment boundaries through logical stress testing

Description URF Application Stress Test — adversarial and scalability tests for Unified Rigidity Framework applications, validating limits under load, noise, and edge cases.

Adversarial testing of LLMs on constraint satisfaction deadlocks

9-stage enterprise development pipeline for Claude Code. TDD, adversarial testing, mechanical verification. Any stack.

Comprehensive AI red teaming index: tools, frameworks, benchmarks, datasets, and vulnerability leaderboards for LLM safety and adversarial testing.

Identified critical AI governance gaps: no adversarial testing, undocumented third-party models, and missing incident response. Delivered roadmap to secure high-risk KYC and transaction monitoring systems against evolving threats.

Red team toolkit for stress-testing MCP security scanners — find detection gaps before attackers do

Compliance-focused vulnerability probes for NVIDIA garak, targeting LLMs in regulated industries (CMMC, NIST, HIPAA, DFARS)

Adversarial testing and robustness evaluation for the Crucible framework

LLM-powered fuzzing and adversarial testing framework for Solana programs. Generates intelligent attack scenarios, builds real transactions, and reports vulnerabilities with CWE classifications.

A governance doctrine for AI systems based on explicit oversight. Externalizes trust and uncertainty into auditable, adversarial, and constrainable layers. A design framework, not an implementation guide.

Generate adversarial pytest tests using LLM. Tries to find edge cases in your Python code.