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.

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

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

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

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)

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

Adversarial testing of LLMs on constraint satisfaction deadlocks

Extremely hard, multi-turn, open-source-grounded coding evaluations that reliably break every current frontier models (Claude, GPT, Grok, Gemini, Llama, etc.) on numerical stability, zero-allocation, autograd, SIMD, and long-chain correctness.

A dependency-aware Bayesian belief gate that resists correlated evidence and yields only under true independent verification.

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

Forensic-style adversarial audit of Google Gemini 2.5 Pro revealing hidden cross-session memory. Includes structured reports, reproducible contracts, SHA-256 checksums, and video evidence of 28-day semantic recall and affective priming. Licensed under CC-BY 4.0.

Adversarial testing and robustness evaluation for the Crucible framework

Analysis of ChatGPT-5 reviewer failure: speculative reasoning disguised as certainty. Captures how evidence-only review drifted into hypotheses, later admitted as review-process failure. Includes logs, checksums, screenshots, and external video.

Adversarial plan verification for Claude Code

🔒 Simulate adversarial behaviors to test and strengthen MCP defenses without real exploitation or risk, ensuring robust security evaluations.

Domain-expert evaluation framework for AI judgment quality in healthcare investing