DARWIN
zju-llm-safety/darwinEvolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…
adversarial-attackai-securitydefensive-tools+5
81
zju-llm-safety/darwinEvolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…
stardust457/sldrDefense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…
zju-llm-safety/ascentFine-tuning framework that applies first-order optimal safety calibration and periodic recalibration to LLMs, preserving safety-compatible updates…
azzzzliao/aegis-audio-defenseDefense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at…
zjuwyh/shadowmemDefensive framework that maintains a safety-focused shadow memory to detect and block prompt-injection and long-horizon threats against LLM agents…
gpt-laboratory/trustworthyragAn Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.
danielbohannon/revoke-obfuscationPowerShell Obfuscation Detection Framework
opposum0112/cusimanseComposable research-contract and YAML-recipe framework for agent-operated security experiments on disposable compute
alex66366/odpureBlack-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…
xhowenma/ropeDefense framework enforcing routed origin policy to prevent indirect prompt injection in tool-using LLM agents, with deterministic origin checks and…
didi/kemonAn Open-Source Pre and Post Callback-Based Framework for macOS Kernel Monitoring.
corelight/threat-hunting-guideStructured guide to threat hunting using Zeek logs, aligned with MITRE ATT&CK framework for proactive detection of adversary tactics and techniques.
c2dc/anomaly-flowFramework for implementing Network Intrusion Detection Systems (NIDS) aimed at identifying anomalies in network flows using Federated Learning models.
jepsen-io/duckdbJepsen-based transactional correctness testing framework for DuckDB, detecting isolation anomalies like G2-item and SSI violations via randomized…
owasp/odtmOWASP Ontology-driven Threat Modelling framework