Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]
-
Updated
Jan 23, 2025 - Python
#
jailbreaking
Here are 23 public repositories matching this topic...
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
-
Updated
Nov 24, 2025 - Python
AI red teaming, jailbreaking, and all forms of adversarial attacks for security purposes
-
Updated
May 22, 2026 - Python
A comprehensive security benchmark for evaluating infrastructure-layer defenses in MCP-based AI agent systems
-
Updated
Apr 18, 2026 - Python
The official Python library for the OpenGuardrails API
jailbreaking pii guardrails prompt-injection llm-security data-leakage-prevention llm-safety openguardrails
-
Updated
Oct 20, 2025 - Python
[ICLR 2026] ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
-
Updated
Sep 30, 2025 - Python
🧪 Evaluating LLM Robustness with Manipulated Prompts
python ai python3 jailbreaking large-language-models prompt-engineering llms prompt-injection gen-ai genai llm-security llm-evaluation genai-evaluation prompt-attacks
-
Updated
Sep 26, 2025 - Python
Multi-agent system for query processing with safety verification and critique built with Google A2A protocol, Google ADK, Llama Prompt Guard 2, Gemma 3 and Gemini 2.0 Flash.
agent ai google-cloud gemini llama jailbreaking adk googlecloudplatform google-cloud-run vertex-ai llm aisecurity genai gemma3 agentdevelopmentkit
-
Updated
Jun 1, 2025 - Python
Comprehensive, auto-updating literature review of GenAI & LLM security research, standards, tools, and resources. 100+ curated entries with interactive webapp.
owasp cybersecurity jailbreaking ai-safety literature-review red-teaming machine-learning-security ai-security adversarial-ml mitre-atlas prompt-injection llm-security genai-security agentic-ai nist-ai-rmf
-
Updated
May 25, 2026 - Python
Context Window Security Scanner — automated red-teaming and jailbreak probing for LLMs. The SQLmap of context windows.
-
Updated
Feb 22, 2026 - Python
python nlp benchmark sqlalchemy persuasion jailbreaking multi-agent-systems ai-safety ai-agents conversational-ai adversarial-attacks fastapi large-language-models llm-safety
-
Updated
Sep 27, 2025 - Python
Jailbreaking Large Language Models for Vietnamese language
-
Updated
Jun 6, 2025 - Python
A hobbyist proof-of-concept exploring attention inter-head instability.
-
Updated
Sep 14, 2025 - Python
Automated daily ecosystem tracking for credential-guard plugin and security initiatives in AI Agents
-
Updated
May 25, 2026 - Python
Severity-weighted LLM safety evaluation suite. Measures absolute refusal robustness across prompt injection, jailbreaking, data exfiltration, toxicity, and malware generation — with risk-adjusted category weights and a custom model-graded scorer.
-
Updated
May 23, 2026 - Python
Collection of evals for Inspect AI
-
Updated
May 23, 2026 - Python
🔒 Real-time security monitoring across 50+ AI/ML repositories. Track vulnerabilities, CVEs, and security initiatives using TinyLlama AI classification. Big Model Radar format reports.
open-source security cve jailbreaking ai-safety security-dashboard vulnerability-scanner red-teaming ai-security security-analytics ai-ml vulnerability-tracking github-monitoring mlsecops prompt-injection llm-security threat-tracking ecosystem-tracking
-
Updated
May 25, 2026 - Python
-
Updated
May 15, 2026 - Python
Improve this page
Add a description, image, and links to the jailbreaking topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the jailbreaking topic, visit your repo's landing page and select "manage topics."